TILens Daily Edition 2026-10-15 Filters: topic=ai-research, github=hidden Stats: 1222 articles, 7 sources, 1215 research papers Top topics: AI, AI Research, Information Retrieval ## News - True Positive Weekly #182 Source: true-positive-weekly Topic: AI (+AI Research) URL: https://aiweekly.substack.com/p/true-positive-weekly-182 - 😸 Gemini now screens scam texts Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/gemini-now-screens-scam-texts-03ac/ - An AI Label Can Change What People Believe, Even When the Content Is True Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/an-ai-label-can-change-what-people-believe-even-when-the-content-is-true/ - GPT-6 Passed One Safety Test at 99.99%. Another Told a Different Story. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/gpt-6-passed-one-safety-test-at-99-99-percent-another-told-a-different-story/ - Grok Voice Says It Resolves 70% of Starlink Calls. What Counts as Resolved? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/grok-voice-starlink-call-resolution/ - The Next AI Cybersecurity Problem Could Run on Cheap TV Boxes Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/the-next-ai-cybersecurity-problem-could-run-on-cheap-tv-boxes/ - Everything That Happened in AI Today (Thursday, October 15, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-thursday-october-15-2026/ ## Research - Jev Your Engines: Seven Open Decision Models vs. a Generative LLM Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/jev-your-engines-seven-open-decision-models-vs-a-generative-llm/ - What OpenAI’s 719 Math Papers Mean for Data Science Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/what-openais-719-math-papers-mean-for-data-science/ - How Many Guesses Does It Take to Crack an AI's "Random" Number? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-many-guesses-does-it-take-to-crack-an-ais-random-number/ - I Tested Four Ways to Give an AI Assistant a Memory. The Obvious One Was the Worst Value. Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/i-tested-four-ways-to-give-an-ai-assistant-a-memory-the-obvious-one-was-the-worst-value/ - From Global to Tail Convergence: Dynamics of $\alpha$-Stable Score-Based Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19773 - Online Tokenization with Optimal Delay in Linear Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19139 - OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19660 - MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19679 - One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20576 - Bridging the Topological Divide: Dual-Branch Graph Distillation with Semantic Priors for Robust Cold-Start Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19578 - Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15470 - How Many Ranks Does a Token Need? A Noise-Floor Squelch for Rank-One LoRA Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19033 - Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise Assignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09369 - Spectral structure learning for clinical time series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.11680 - Conformalized Physics-Informed Weak Regression for Parameter Estimation in Epidemic Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19058 - LLMs program using Reusable and Composable Abstract Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19238 - Towards Training and Inference of Graph Neural Networks in Graph Databases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19142 - StaRPO: Stability-Augmented Reinforcement Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08905 - When Does Momentum Help in Reinforcement Learning with Verifiable Rewards? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20413 - Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-as-Reward RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11669 - Predicting Unseen Scientific Interactions: Conditional Flow Models Hallucinate Non-Additive Effects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20288 - MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19330 - HGRP: Heterogeneous Graph Neural Network for Routability Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20209 - Fully sequential Gaussian process regression for preference learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19391 - FlowSep-RF: Rectified Flow Matching for Single-Channel Radio-Frequency Signal Separation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20269 - Automated Assembly Instruction Generation from CAD Models Using Grounded Large Language Models: A Human-in-the-Loop Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11896 - Divergent Paths: Learning an Outcome-Predictive Representation of LLM Agent Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19614 - Investigating Behavior Cloning from Few Demonstrations for Autonomous Driving based on Bird's-Eye View in Simulated Cities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20203 - State Space Models Naturally Produce Time Cell and Oscillatory Behaviors and Scale to Abstract Cognitive Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.13638 - Risk-Controlled DFT Selection for Machine-Learned Interatomic Potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19630 - Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22299 - A Computational Framework for Modelling Organisation-Level Semantic Identity from Longitudinal Textual Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29584 - Popularity Trajectories and Mixing Patterns of Urban Venues in Two European Cities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18917 - Geological text descriptions in ill-posed inverse problems: insights from learned hydraulic-conductivity inversion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24967 - MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17856 - Scaling Multilingual Mixture-of-Experts: How Language Coverage Changes Capacity and Compute Allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20247 - Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19065 - Wong--Zakai Convergence and FNO Learning for Stochastic Volterra Equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18939 - Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2311.04902 - Did the LLM Answer the Question? A Semantic Reconstruction Game for Jailbreak Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19306 - ReproBAIT: Can coding agents build their own biological AI tools? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19810 - Universal Sample-Based Embeddings of Higher-Order Objects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19899 - HRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12393 - Contrastive uncertainty learning for robust multi-structure segmentation in lower-pelvic MR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20251 - CAST: History-Adaptive Spectral Clipping for LLM Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19761 - One-Step Prediction Fidelity Is a Poor Proxy for Planning Performance in JEPA World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19375 - Learning to Design Convex Relaxations for Nonconvex Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16948 - PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32429 - InstructPro2: Natural Language and Biological Grounding Guided De Novo Protein Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19592 - Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.04473 - LIME: Learning Intent-aware Camera Motion from Egocentric Video Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02417 - Reinforcement Learning via Advantage Guidance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19783 - ReAl: Refine neural operators via aligning dynamical flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20369 - Embedding Geometry Shapes LLM Routing: Tracing Failure Modes and Improving Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19198 - Efficient Test-Time Adaptation For Robot Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20318 - MorphingNet: Symbolic Regression Where the Network Is the Formula Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19942 - Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19364 - On Global Joint Lower Bounds in Zeroth-Order Nonconvex Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19652 - Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20497 - CASI: Credit Assignment via Set Intervention for Agentic Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20293 - Trainable at Depth, Solvable at Small Size: What the Loss Surface of a Polynomial Activation Dictates for Designing, Initializing and Training Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20069 - Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08077 - Exploring Interpretability in Deep Learning-Based Forest Classification - Separating Similar Forest Classes using Sentinel-2 Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19270 - Memory Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28399 - Medical Imaging Classification with Cold-Atom Reservoir Computing using Auto-Encoders and Surrogate-Driven Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06727 - DEFlow: Deep Equilibrium Flow Maximum-Entropy Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16597 - Train to Stitch: Topology-Preserving Regularization for Interoperable Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19401 - SafeAdapt-Poker: Counterfactual Risk Calibration for Budgeted Adaptation under Opponent Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20473 - Selective Growing Q-Networks (SGQN): An Analysis of Adaptive Action Grids in Decoupled Q-Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20463 - QASP: Query-Adaptive Robust Vector Search Policy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.29606 - Principled Design of Expected Improvement for Continuous Simulation Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18434 - VASPO: Self-Distillation with Privileged Value Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20516 - Sequential Learning-Based Physics-Informed Neural Network Modeling for Parameter Estimation on a Power Converter Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20041 - Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09015 - Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19525 - Two-stage Residual Learning for Modelling Strength-Informed Optimisation of Thermal Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19539 - Rational Transductors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.07599 - Hypothesis Selection via Weighted Medians Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20375 - TimeWarp: Evaluating Web Agents by Revisiting the Past Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.04949 - SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19931 - What Do Foundation Models for Market Microstructure Learn? A Controlled Study with Synthetic Limit Order Books Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20104 - Hide and Seek: HIDE Concepts to SEEK explanations for black box models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13935 - Demystifying On-Policy Distillation: Where Does the Teacher's Advantage Live? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19145 - Mechanistic Circuit Identification for Controllable Data Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24065 - DAGFormer: Global Topology Prediction for Transformer Cross-Layer Connections Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19625 - Token Utility for On-Policy Distillation via Local Trust-Region Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18883 - Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19439 - ActMOF: Mapping Reticular Synthesis through Active Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19404 - Historical-Feature Residual Adaptation for Sequential Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19315 - Policy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19372 - TANGO: RNA Topology and Geometry Co-Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20277 - Asymptotically Exact Negative Guidance of Diffusion Models via Positive-Unlabeled Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19802 - Robust Explanatory Analysis for Structured Optimization Networks (REASON) in Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19378 - A Large-Dimensional Analysis of Least-Squares Federated Learning via Generalized Total Variation Minimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20075 - Articulation Upper Bounds for Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19721 - Trustworthy AI Must Account for Interactions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.07170 - Flow Matching with Uncertainty Quantification and Guidance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10326 - What Information Buys in Active Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19046 - New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19712 - ProximalFM: Amortized Proximal Causal Inference under Hidden Confounding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08078 - Dimension-Optimal Dynamic Regret in Exp-Concave Online Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20187 - Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19053 - Langevin Flow Maps: Efficient Molecular Dynamics and Transition Path Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05998 - Delay Complexity Dimension: Learning with Delayed and Censored Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18935 - Theoretical and Practical Advances in Hierarchical Bayesian Deep Learning Methodology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19074 - Adversarial Reinforcement Learning for Robust Planetary Landing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20252 - When Does the Dependency Graph Help Code-to-Architecture Mapping? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19769 - ReGRA: Residual-Gradient Adaptation for Complementary Low-Rank Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19700 - Typed Decision Models on Tabular Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19536 - MA-Bench: Measuring Operational Planning in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19138 - Sharp Statistical Thresholds for Attributed Gaussian Graph Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23305 - Beyond DFT electronic band structures via dual-space orbital learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19919 - Strong Gaussian Approximation of Constant Learning Rate SGD: Bias and Trajectory Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14567 - On Inherent Privacy of Posterior Sampling: A Unified R\'enyi-Divergence Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19573 - How Inner Optimizers Shape Replica Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19064 - Attention Transfer Is Not Universally Effective for Vision Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07191 - Optimizing Sparse Boolean Rule Networks using Mixed Integer Linear Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20170 - Exact Scaling Laws for a Random-Features Bigram Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19281 - When is a System Discoverable from Data? Discovery Requires Chaos Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.08860 - TEX-MEX: Similarity-Guided Temporal Contrastive Learning for Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19557 - More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19789 - Contextual Credit Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19103 - Causally-Constrained Probabilistic Forecasting for Time-Series Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17998 - Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19685 - Unification and Optimization of Robust Supervised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28165 - HankelKANet: Lightweight Path Loss Estimation via Physics-Inspired Hankel Convolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19524 - Learning Graph Energies for Finite-Time Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19946 - Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19768 - Loss Curvature as a Sampling-Free Proxy for Memorization in Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19042 - KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20117 - Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13319 - Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20009 - Privacy-Preserving GNN Inference on Financial Transaction Graphs via Homomorphic Encryption Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18054 - Extreme-Scale Super-Resolution of Homogeneous Turbulence from a Single Realization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20305 - CktHGVAE: A Symmetric Design/State Heterogeneous Graph Variational Autoencoder for Transistor-level Analog/Mixed-signal Circuit Design and Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19508 - AtomSearch: Evidence-Grounded Tree Search for Agent Skill Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19951 - Limits of Statistical Assurance for Embodied and Agentic AI under Adaptive Adversaries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18948 - TabFORGE: A Tabular Foundation Model for Generative Modelling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09424 - AI Models Can Provably Hide Arbitrary Capabilities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13928 - Rule-based and reinforcement-learning policies for resource allocation in a pediatric echo lab: a simulation study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.06297 - RM-OPD: On-Policy Distillation for Generative Reward Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20174 - Energy-Based Models For Speech Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.12765 - The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refusal Behavior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.12066 - SKG: A Law-Induced Engine from Inference to Induction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19505 - NeuronDiscover: Agent-in-Twin for Mechanistic Discovery in Neuronal Microenvironments with World Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35338 - Geometric Kernel Diversity: An Axiomatic Diversity Measure in Euclidean Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19570 - Test-Time Forecasting: Recurrent Depth Enables In-Context Dynamics Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19552 - Hyperspherical Contrastive Representations Unlock Planning and Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20409 - Seeing at the Edge: Energy Characterization of Vision-Language Model Inference on Edge Platforms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20136 - Who Should We Listen to More? Welfare-Aware Preference Acquisition for Pluralistic Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19035 - DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32363 - Minimax estimation of the pseudo-spectral gap of continuous Markov chains, with applications to empirical concentration bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20007 - Harness Policy Distillation: Aligning Agent Policies with Runtime Semantics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20261 - Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31111 - Beyond Sustainable Development Goal (SDG) Accelerators: Directed Evidence for Adaptive Sustainability Portfolios Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.20875 - TIMERSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19725 - The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24041 - Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08519 - EduBehaviors: Assertion-based Schemas for Auditable Coding of Educational Dialogues Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27043 - Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20071 - Where to Start, How to Move: Analyzing Curricula under GRPO for Long-Horizon LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19349 - Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17883 - BFHD: Bidirectional Feature Harmonization Decomposition for Heterogeneous Clinical Assessments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19352 - Learning to Select Features with Manifold Deep Unfolding PCA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19436 - OrionMoE-v1.0: A Mixture-of-Experts Foundation Model for Tabular In-Context Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20418 - The Impact of Detector Architecture, Model Scale, and Scene Density on Multi-Pedestrian Tracking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19369 - LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19975 - Comprehensive Comparisons of Reinforcement Learning Algorithms in Autonomous Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19429 - Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20179 - Your Transformer Is Secretly Elastic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20588 - Genesis Steering: Better Activation Steering Through Training Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19114 - Digital Self-Interference Cancellation for In-Band Full-Duplex Systems Based on Transformer Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19490 - Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07853 - Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20607 - Self-Conditioning Enables Deep Sequential Reasoning in Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19628 - RoboSimStudio: An Interactive Toolkit for Human and Agent Rapid Real2Sim of Robot Manipulation Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18835 - Counterfactual Gate-Support Decomposition: Separating Selection from Redistribution in Training-Data Filtering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19343 - Co-Evolving Acting and Forecasting for Language Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20597 - Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18881 - ProtoPur: Prototype-Purity Pseudo-Labeling for Weakly Supervised Instance Learning in Pathology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15669 - On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19892 - Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02626 - From Detection To Anticipation: Continuous Onset Forecasting For Stuttered Speech Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19235 - CTIA-ODE: Continuous-Time Inter-Variable Attention for Long-Term Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19831 - EMG-FM-Bench: A Comprehensive Benchmark for Foundation Model Transfer and Adaptation on Electromyography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06450 - A Versatile Variational Quantum Kernel Framework for Non-Trivial Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.10831 - The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09200 - GLL: A Differentiable Graph Learning Layer for Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.08016 - MIPS: Mitigating Mode Collapse in Reinforcement Learning for Large Outcome Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19457 - A proximal gradient algorithm for composite log-concave sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12461 - On the Convergence of Semi-Gradient TD: A Mean Field Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20014 - Adaptive Computation with Conformal Certification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19189 - Beyond Expert Rankings: Contrast Calibration for Mixed-Precision MoE Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20353 - Readout Scaling Shapes Sparse Feature Recovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18462 - Neural Wasserstein Splines: Representation-Invariant Second-Order Priors for Trajectory Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19878 - Continuum Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20586 - A Bregman Proximal Viewpoint on Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20120 - What Does Disagreement Mean? A Semantic Identifiability Frontier for Pairwise Preference Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20450 - When Does Depth Help? Understanding Layerwise Inference in Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19814 - Distinguishing Process Change, Instrument Fault and Data-Path Corruption in Streaming Telemetry: A Reference Implementation and Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18904 - An Initial Study of Physiological Markers for Deepfake Speech Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18934 - VaryST: Generalizable Spatio-Temporal Forecasting Beyond the Closed-World Setting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19813 - The Invisible Leash: Why RLVR May or May Not Escape Its Origin Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.14843 - Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF Kernel Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10080 - A Unified and Constrained View of Regularization-Based Robust Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13050 - Ideological Bias in LLMs' Economic Causal Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21334 - Latent Compaction with Test-Time Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20582 - Safe-FCL: Continual Risk Awareness and Fine-Grained Safety Aggregation for Federated Continual Learning of LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19968 - Generalizing Identifiability Results in Causal Discovery from Complete Data to Missing Data Settings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19211 - Fractional is Better: Learnable Derivative Orders in Neural Operator Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20363 - Explorer-Zero: Improving Self-Play for Long-Horizon Tasks with Decomposable Verifiable Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19868 - Human and LLM Facilitation in Collaborative Design Meetings: A Computational Behavioral Comparison Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13082 - Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02795 - Towards Modality-Agnostic Seizure Classification: A Unified Deep Learning Framework for Heterogeneous EEG and Intracranial EEG Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16596 - Posterior Frequencies and the Cost of Not Fitting: A Correction to a Memorization Lower Bound Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20402 - Spectral-MoE: Heterogeneous Per-Layer Expert Utilization in Dense-to-MoE Conversion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19232 - Energy Consumption Analysis of Discrete Diffusion and Autoregressive Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19855 - Verifier-Grounded Agentic RL for Provably Correct Code Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19298 - Learning Provable Neural Network Observer for Uncertain Dynamical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30819 - Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20606 - HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19654 - Structured Multi-Level-Set Inversion for 3-D Electromagnetic Inverse Scattering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08594 - Learning by Examples: Power Grid Steady State Analysis with a Tabular Foundation Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20462 - What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19731 - From Causal Graphs to Markovian States: Multi-Order State Exposure for Deep RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07057 - Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20350 - Learning, Fast and Slow: Towards LLMs That Adapt Continually Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12484 - FUSE: Fairness-aware Update Screening against Byzantine Exploitation in $q$-Fair Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20264 - Long-Horizon RL Needs Muon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20256 - Imagining Goals with Geometric Horizon Models for Policy Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19129 - VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20509 - Detection of Potato Plant Leaf Diseases using Convolutional Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20544 - JointServe: Serving Multi-Model Agents on Memory-Constrained GPUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19822 - Cross-View Time-Frequency Diffusion for Extreme-Aware Time-Series Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17407 - Blackknife: Query-Free Black-Box Rewiring Attacks on Heterogeneous Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29240 - Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15482 - PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19605 - Convergence Rates of Gaussian Process Thompson Sampling for Efficient Global Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19925 - X-Safe: Embodiment-Agnostic Safeguarding for Robot Arm Manipulation Policies via Action Masking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22278 - Continual Learning for Reliable In-Sequence Molecular Communication Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20426 - Learning Who Benefits Most: Multi-Treatment Causal Ranking for Population Health Stratification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19782 - A Graph-Based Analysis of Comparability, Scale, and Attribution in Private Transformer Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19607 - PMO-Dock: Benchmarking Docking, Specificity, and Generalization in Molecular Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19011 - SPARK: Learning from Verification in Speculative GRPO Rollouts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04962 - hyperbolix: Hyperbolic Deep Learning in JAX Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28248 - From Clicks to Intent: Cross-Platform Session Embeddings with LLM-Distilled Taxonomy for Financial Services Recommendations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26277 - TRACER: Trace-Regularized Training Against Indirect Prompt Injection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19133 - Training Language Models to Fail Gracefully Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20401 - Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19636 - The Physics Is the Network: Fast, Training-Free Neural Emulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20525 - A Unifying Framework for Concept-Based Representational Similarity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09653 - Noise-Aware Differentially Private Variational Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.19371 - On the Optimisation Landscape of Overparameterised Weighted MMD Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19861 - Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19359 - Integrated Novelty Detection Systems: From Sensor Networks to Multi-Novelty Computer Vision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19347 - SuperAI: Merging Capabilities Across Heterogeneous Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15322 - High-Probability Regret Bounds for Feel-Good Thompson Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19513 - Narrowing the Collaboration Gap, Probably Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19215 - Platonic Projection Structures: Operator-Induced Observability in Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05175 - AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14959 - From Spectral to Frobenius: When Muon Loses Its Spectral Implicit Bias Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20112 - Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00191 - Who's Behind the Text? Robust Model Authorship Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19583 - Gauge-Invariant, Parameter-Insensitive Regularization for Potential Recovery from Flow on Directed Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13609 - GQLA: Group-Query Latent Attention for Hardware-Adaptive Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15250 - Projected Wasserstein-Fisher-Rao Flows for Hawkes Background-Intensity Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19588 - SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21649 - Structural Pass Analysis in Football: Learning Pass Archetypes and Tactical Impact from Spatio-Temporal Tracking Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28916 - When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15959 - STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07036 - FireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19191 - Inverse Reasoning Models for Efficient Post-Training and Verification from Answer-Only Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18878 - Efficient contextual partial monitoring with general function approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19804 - Bellman Conformal Inference: Calibrating Prediction Intervals For Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.05203 - Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19121 - Generation of data on discontinuous manifolds via continuous stochastic non-invertible networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2112.09646 - Enhancing Latent World Models with Associative Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19683 - Does Pretraining Teach Chemical Language Models Chemistry? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18651 - RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08234 - Physics-Integrated Operator Learning via Gaussian Splatting Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24049 - Choosing the Number of Attention Heads from Intrinsic Dimension: A Small-Scale Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19966 - Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.05559 - CARD: Closing the Teacher-Student Loop for Adversarial Robustness Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19911 - When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04861 - Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18106 - Predictively Oriented Gaussian Process Posteriors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03201 - GBTSVR: Twin Support Vector Regression via Granular Ball Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20053 - INTACT: Inducing Latent Reasoning on a Frozen Backbone Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19568 - CausalDS: Benchmarking Causal Reasoning in Data-Science Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08093 - ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18088 - Edgewise Envelopes Between Balanced Forman and Ollivier-Ricci Curvature Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13535 - Are We Overthinking One-Step Generation? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20331 - Multimodal Medical Image Parsing with Task-Specific Low-Rank Adapters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19901 - AgentWorld: A Data Factory for Training LLM Agents from Multi-Turn Interactions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09138 - Bayesian Learning to Select Fair Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20514 - Deep kernel hedging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34474 - A Unified Response Framework for Questions and Tutoring Dialogues Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19532 - Rethinking One-Shot Federated Graph Learning: Training-Free Statistical Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06154 - From Copying to Composition: How Language Models Develop In-Context Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19113 - Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.16939 - Selective Next-Location Prediction with MetaModelSelect: A Lightweight Post-Hoc Confidence Metamodel Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19394 - Evidence-Anchored Overdose Death Prediction from Death Investigation Reports Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19556 - The Neuro-Physical Inverter: A Modular Framework for Magnetotelluric Inversion Coupling Ensemble Conditioning with Residual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03225 - Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20243 - Deep Time-series Forecasting Needs Kernelized Moment Balancing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00717 - FACT: Failure-Aware Causal Training for World-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10232 - Interpolation of GEDI Biomass Estimates with Calibrated Uncertainty Quantification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16834 - Parameter-Efficient Temporal Domain Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11965 - FinGREAT: Evaluating LLMs on Financial Graph-guided Retrieval And Typing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19240 - Reinforcement Learning via Fixed-point Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12848 - Tracing Morphology, Semantics, and Divergence in Language Acquisition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19041 - How Far Can Coding Agents Go in Visual Generation? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19025 - On the Dynamics of Delayed Generalization in Linear Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08302 - Semi-Amortized Bayesian Inference with Reusable Local Posteriors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18945 - A finite-element-inspired bipartite graph learned simulator for manufacturability assessment in large-deformation sheet forming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22845 - Noisy-Label Calibration with Multiple Unreliable Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19543 - Target-Token Asymmetry Can Masquerade As Depth Specialization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19344 - When Does Task-Aware Imputation Matter? An Analysis of Robustness Under Train-Test Mismatch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20342 - Anticipatory Evaluation of Language Models: Predicting LLM Benchmark Scores from Descriptions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.20645 - Constitutive parameterized deep energy method for solid mechanics problems with random material parameters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26030 - State-Matched Sequence Conformal Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19484 - Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19362 - Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.26370 - MvFFN: Multi-view Floor plan Feed-forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14315 - ProtModernBERT: Compute-Efficient Protein Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19738 - RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17867 - Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01449 - Structure-aware Bayesian full waveform inversion via diffusion-regularized Stein variational gradient descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19187 - Learning Across Temporal Graph Representation Silos Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19576 - Multi-Sensitive Distributional Fairness: Joint Wasserstein Audits and Shapley Allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19252 - MAPLE: A Multi-Axis Parametric Knowledge Extraction Lens for LLM Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19827 - Imaging-anchored Multiomics in Cardiovascular Disease: Integrating Cardiac Imaging, Bulk, Single-cell, and Spatial Transcriptomics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.07871 - Graph-Enhanced Disease Trajectory Discovery and Temporal Endpoint Forecasting from Longitudinal Electronic Health Records Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20502 - Resolution Allocation with Learnable Resizing and Spectral Filter Parameterization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20274 - Who Sets the Pace of Judge Hacking? Judge Capability versus the Policy-Judge Gap Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15778 - What Does a Discrete Diffusion Model Learn? One Reverse Process in Three Coordinates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05381 - Refined Topology-Pass Scheduling: Damped Trust-Region Compensation for Dynamic k-NN Graphs in SE(3)-Equivariant Structure Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19246 - Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03172 - Data Density Scaling Laws for Image Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19013 - The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36484 - AI-Driven, Timing-Aware Power Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18890 - Lost in Translation: Why Lower Bias Scores Don't Mean Fairer Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20479 - Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.01867 - Toward Agents That Reason About Their Computation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.22833 - From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message Passing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03709 - BrainDyn: A Sheaf Neural ODE for Forecasting and Generating Brain Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19324 - Natural Code Transformation Confuses Agents in Vulnerability Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14350 - A Two-Level Clinical Novelty Prioritization Framework for Disease Trajectories Discovered from Longitudinal Electronic Health Records Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20512 - Student Copula Markov Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19135 - What You Sign Is Not What You Run: The Verifiability Gap in Quantized LLM Supply Chains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19498 - Does Depth Survive Composition, and Can a Router Use It? Adaptive Compute in Latent World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10203 - NOMOS: Compiling Written Policies into Statically Verified Tool-Call Gates for LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11030 - Beyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19084 - Calibration and Risk-Budgeted Decisions with System One Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19811 - Function-Space Temporal Self-Distillation for Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19687 - Bayesian Causal Forests for Zero-Inflated Continuous Outcomes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18889 - The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18933 - TopicMerge: A Divide and Conquer Approach to Topic Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19323 - Generative Actor-Critic with Soft Bridge Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08733 - Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14706 - Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19766 - Uncertainty-Aware Probabilistic Constrained Clustering from Entangled Pairwise Supervision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12027 - tidyHEBO: Improving the Robustness of Heteroskedastic Evolutionary Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10669 - The Statistical Benefits of Multiple Responses for Learning from Demonstrations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33291 - DTDD: Divergence-Triggered Dynamic Distillation for Reliable On-Policy Supervision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19302 - L3M: A Verifiable Harness and Runtime for Self-Extending and Self-Improving Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19591 - LLMs Can Design Near-Optimal OR Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27296 - MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20238 - Into the Unknown: Benchmarking AI agents on open scientific research problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19159 - IR-PRM+ with Previous-Utility Prediction: Constant Regret and Best-Iterate Convergence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19016 - TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32384 - Steering Diffusion Models to Rare Events with Sequential Monte Carlo Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08652 - MolHop: Scaffold-Hopping Molecular Design with Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19920 - Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11152 - Empirical Boundaries of Reservoir Computing for Few-Shot Sequence Pattern Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19997 - Learning in Strategic Queuing with Geometric Recharge: From Bandits to Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19179 - Discrete Diffusion Models are Minimax Optimal Under Sparsity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19020 - Interaction-as-a-Judge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17895 - W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19411 - ChemArgus: Automated Scientific Diagnostics for Lab-Grade Multimodal Chemistry Reasoning: A Frontier Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20012 - The minimal width of neural networks and immersions of real projective space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20229 - Non-asymptotic Convergence of Average-reward Q-learning with Options Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20347 - Driving, Fast or Slow? Neuro-Symbolic Guidance for Motion Prediction in Multi-Modal Ground Mobility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15251 - Provable Transformer Context Compression for In-Context Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20004 - Continual pretraining Prostate MRI ViT Encoder for task alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20217 - Is Flow Matching Just Trajectory Replay for Sequential Data? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08318 - PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21139 - Context Value Informed In-Context Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.23209 - Few-Shot Adaptation for Anomalous Sound Detection at Low False-Positive Rate Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19893 - NeuronSifter: An Agent-in-Twin for Prioritizing Central Nervous System Interventions with World Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35445 - HARP: Efficient Data Selection for Finetuning Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07690 - Learnable Hodge-Laplacian Driven Mixture of Experts for Steady-PDE Surrogates on Coarse Unstructured Meshes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20585 - SNACK: A Sequential Notation Framework for Probabilistic Graph Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19781 - Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29403 - Scaling Cheap Synthetic Pretraining Improves Indoor Radio-Map Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19015 - How Far Are We From True Auto-Research? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19156 - In-Context Batch Black-box Optimization via Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20138 - Annealed L\'{e}vy Diffusion via Gaussian Surrogate Reverse Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19692 - Comparing SGLD and a fixed-noise predictor-corrector adaptation in canonical joint energy-based models on CIFAR-10 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05025 - Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19095 - Backpropagating Verifier Rewards Through Continuous Flow Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19080 - Do Vision CIL Methods Transfer to Protein? A Diagnostic Benchmark of Frozen Protein Encoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18879 - Dictionary learning for Kernel EDMD Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25572 - Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19832 - Optimization for One, Feasibility for Most: Decoupling Optimization from Feasibility in Chance-Constrained Programs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19027 - TIDES: Implicit Time-Awareness in Selective State Space Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09742 - Training Dynamics of Transformers on Unbounded Inputs: Attention Learning Can Lag Output Layer Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20337 - Riding the Fixed-Point Curve: Image Classification in the Continuous Thought Machine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19220 - Wrong Operator or Blind Design? A Post-Training Diagnostic for Physics-Informed Coefficient Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16925 - Decoupled Marginal Sharpening for Training-Free Inference-Time Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20483 - Tracking a Small Set of Experts in Online Convex Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20416 - MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00720 - ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition Gaps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20532 - Participation-Sensitive Convergence and the Fragment First, Converge Later Pattern in Asynchronous Online Learning: A Topological Analysis Across 22 OULAD Courses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01738 - Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18990 - Learning Individual Scientific Taste with Privileged Hindsight Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19719 - FOLD: Position-Free Far Memory with Local Order for Long-Context Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20392 - HRTF Upsampling and Personalization via Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20400 - The Accuracy Well: Nonmonotone Accuracy Dynamics at Vanishing Initialization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20439 - ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09009 - Neural Supervised Clustering for Learning Individualized Treatment Rules with Many Treatments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19104 - Graph Coarsening Enables Escaping Local Optima in Compute-Constrained Nonconvex MAX-CUT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19043 - Smart Alone, Blind Together: Why Accuracy Fails to CertifyTheory of Mind in Multi-Agent Teams Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19051 - From Plato to Aristotle: Toward a General Theory of Representation Hypotheses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20286 - Do Perturbation Predictors Learn Gene Interactions? Diagnosing Extrapolation in Agentic Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18880 - AdaPCLA: Adaptive Prior-Calibrated Logit Adjustment for Long-Tailed Longitudinal EHR Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12645 - Outcome-Routed Distillation and Reinforcement Learning for Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19271 - RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19385 - Exhaustive Canonical Skeletons Generation: A Formal Dataset for Decomposable Symbolic Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20108 - Revisiting Simple Baselines for Relational Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20534 - Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19743 - Why don't Graph Transformers attend to the same token? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19324 - A Simple Plug-in for Improving Eviction-Based KV Cache Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23258 - Tracking large chemical reaction networks and rare events by neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.10309 - LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10980 - Price of Anarchy of First-Price Auctions in Agentic Markets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20587 - Beyond Time Induction: Structured Conditional Neural Solvers for Parametric Stochastic-Volatility Pricing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19254 - Lag: A Mean-Field Optimal Policy for Online Assignment with Reusable Resources Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19038 - Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASH Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.12355 - Synthetic reaction data from transformation rules for graph-to-sequence pretraining in biodegradation pathway prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19640 - One Size Does Not Fit All: Curvature-Aware Adaptive Perturbation for SAM Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20415 - RELAY: Selective Self-Distillation with Adaptive Hand-off for Rubric-Based Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17623 - Physical Layer Anomaly Detection via Adaptive Gaussian Mixture Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18946 - Lotus: Learning to Understand Time-series by Learning to Forecast Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18877 - Generative Representation Learning for Scalable Latent Tokenization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20533 - A Byzantine-Robust Federated Learning with Nesterov Momentum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.02657 - Comparative Evaluation of Deep-Learning based DoA Estimators for Real-Time ISAC Beamforming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20326 - Dimension-Free Scaling Laws for Size Generalization: An Exponential Separation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19279 - StateCraft: Augmenting Video World Models with Abstract-State Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19795 - Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19883 - Relatively Smart II: Tractable or Semi-Supervised Instance-Optimal Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10886 - Linearly Convergent Algorithms for Nonsmooth Problems with Unknown Smooth Regions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.19465 - Physics-Guided Multi-Fidelity Surrogate Modeling for Natural Supercavity Geometry of an Axisymmetric Conical Cavitator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18886 - Weighted Adjoint Matching: Finetuning Flow Matching Models with Time-Dependent Control Cost Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20035 - Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Owners Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.12010 - Asymptotic Behavior of Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19358 - HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16285 - SpectrumQuant: Spectrum Alignment for LLM Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20303 - Model What Matters: Decision-Guided Selective World Modeling for Language Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19642 - TorchSpin: Differentiable Electron Paramagnetic Resonance Simulation in PyTorch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18924 - Score-Based Training for Energy-Based TTS Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.13771 - Activation Steering Induces Emergent Misalignment: Steering Vector Construction and Comprehensive Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08682 - From Human Corrections to Learned Segmentations: A Critical Mathematical Review of Information, Learning, and Human Effort Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20396 - Memory by Design: Bayesian Layers for Sequence Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31163 - The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20456 - Large-Step Last-Iterate Convergence of Random-Reshuffling Stochastic Gradient Descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19444 - PairIT: Autoregressive Transformers for Low-Data Molecule Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19123 - SPARS: A Stability-Plasticity-Aware Region Selection Framework for Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19876 - Cortex: Consolidating Context into Parametric Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20399 - MMLA-RSI: Recursive Self-Improvement through RTT and RTMA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20294 - Beyond Static Positional Encoding: Bayesian Time-aware Attention for Non-Stationary Long-term Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19603 - Gap Detection: Mitigating Homogenization through Demand and Defensibility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20162 - When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19910 - Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12000 - Average-Reward Policy Identification from a Single Continuing Trajectory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20486 - Every Fixed Metric Has a Blind Spot: A Learned Atmospheric Critic for Scoring Forecast Realism Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18381 - Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBench Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18938 - Diagnosing Low-Confidence Patient Profiles via Localized Harmful Covariate Shift Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19178 - Memory-Efficient Subspace Optimization with Residual Correction: From Momentum SGD to Muon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19844 - Long-Range Distillation: Distilling 10,000 Years of Simulated Climate into Long Timestep AI Weather Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.22814 - NeuroDETR: Multiscale Discrete Spatiotemporal Tokenization for Asynchronous EEG Event Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20349 - NePPO: Near-Potential Policy Optimization for General-Sum Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.06977 - Maximum-Entropy Exploration with Future State-Action Visitation Measures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18965 - Recovering Reliable Supervision via Critique-Guided On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20572 - PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20538 - Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.08464 - Mixed Poisson diffusion models and application to posterior sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20218 - Text-Informed Training Data Filtering for Enhanced Virtual Flow Meter Performance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19860 - Scaling LLM Inference via Parallelism: Throughput-Latency Trade-off Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19405 - Relevance Supervision Can Teach Neural Retrievers to Prefer LLM-Generated Text Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2604.06163 - XViewRank: Overlap-Conditioned Score Fusion for LLM-Augmented Sparse Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.20122 - Plan or Retrieve First? A Scale Study of Tool Discovery Architectures Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.19068 - Virtual-Alloy Physics-Aware Semantic System for extrapolative prediction of perovskite solar cells Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18949 - Retrieve What Helps, Only When It Helps: Agentic Reinforcement Learning for Selective Retrieval-Augmented Machine Translation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.19528 - On the Impact of Graph Neural Networks in Recommender Systems: A Topological Perspective Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2512.07384 - Document-as-Image Representations Fall Short for Scientific Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2604.18508 - Reading the Neighborhood: Text-Attentive Graph Reranking for Automated Subject Indexing Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.20048 - RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.27394 - When RAG Doesn't Help: LLMs for Plausible Material Prediction of Vehicle Components Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18437 - Twenty Days Later: A Pre-Registered Test of History-Based Forecasts of Brand Mentions in Gemini Answers Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.19608 - Retrieval-Augmented Generation to Support Railways Engineering Tasks: A Case Study Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.01244 - Creating SquashFS Images to Support HPC and AI Datasets Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.20578 - ARAFA: An LLM-Generated Arabic Fact-Checking Dataset Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.25833 - RCER: Reconstructing Cross-Evidence Relations for Iterative Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.19398 - When More Documents Hurt RAG: Measuring and Reducing Vector Search Dilution with Domain-Scoped Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.11350 - HEM-Med: A Hierarchical Agentic Memory Framework for Safe Multi-Center Medication Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.20191 - UniRec: Bridging the Expressive Gap between Generative and Discriminative Recommendation via Chain-of-Attribute Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2604.12234 - The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04047 - AdCoEvo: A Co-Evolving Multi-Agent Advertising Delivery System Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.19454 - GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2603.14426 - Data Curation and Model Souping: Unlocking Qwen3-0.6B for MS MARCO Passage Ranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.14816 - IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent Fluctuations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02110 - AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20474 - Scaling Personality Control in LLMs with Big Five Scaler Prompts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.06149 - Computed, not Memorized: Bit-Factorized Identifiers for Efficient Generative Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.17467 - Robust Asynchronous Planning via Auto-Formalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00981 - Beyond State Capacity: Why Retrieval Breaks in Mamba Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19709 - JetSpec++: Foresight Parallel Drafting with Self Refinements Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19792 - Confidently Wrong: Detecting Hallucinations in Financial Question Answering from LLM Internal States Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11414 - Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19696 - ProReviewer: Evidence-Driven Investigation for Scientific Peer Review Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13349 - Phantom Paradoxes: Language Models Treat Unresolved Circular Truth Dependence as Contradiction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12128 - LoopRPT: Reinforcement Pre-Training for Looped Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19714 - Lazy Grounding: Attacking Search Agents with Factual Evidence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30303 - Policy-Conditioned AI-Use Detection: An Evidentiary Framework for Academic Publishing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38427 - AgriJev: Efficient Agricultural Candidate Scoring with Multi-Scale Adapted Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19478 - DischargeBench: Pre-Deployment Evaluation of LLM Discharge Educators through Persona-Grounded Patient Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20827 - From Qualitative Text to Integrated Evidence: The Parallel-Then-Integrated (PTI) Procedure Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19164 - SEA-HELM Audio: Evaluating Multilingual ASR-LLM Pipeline Performance Across SEA-HELM Subsets Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19869 - RCCM: Diagnosing Gains and Harms in Reasoning-Prompt Transfer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19872 - Quality-Aware Self-Correcting Speech Translation on an Edge Device Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07545 - Anuvani-LID: Robust and Calibrated Spoken Language Identification for Indian Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20263 - Majority Bit-Aware Watermarking For Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.03829 - From Structure to Validity: Mechanism-Guided Generation and Refinement of LLM Rubrics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13375 - Why Generate a Click? Plug-in Decision Heads for Web Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20107 - Sparse Autoencoders for Mechanistic Interpretability in NLP: A Critical Survey of Recoverability, Interpretability, and Utility Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20139 - Beyond Reachability: A Relation-Semantic Reasoning Framework for Biomedical Multi-hop QA Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19754 - Truthful and Expected-Payment-Optimal Model Routing in Graph-Based Agentic Workflows Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19316 - $\tau$-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19560 - Towards Efficient Simultaneous Inverse Text Normalization with Pretrained Text-to-Text Language Model and Read-Tag-Write Policy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19492 - DCGC: Draft-Conditioned Global Correction for Complex Reasoning with Masked Diffusion Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25428 - Lexical Persistence Without Semantic Entrenchment in AI Agent Communities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20365 - SecJev: Bringing Security Expertise to System One Decision Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03073 - DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19118 - ActICL: Post-Training for Agentic Multimodal In-Context Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19475 - Explain Like I'm 5 or Whatever I Choose: Evaluating the Potential for Interactive Complexity in Language Model Responses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06788 - Delta Tokenizer: Reference-Identical Tokenization of Session Deltas and Segment-Parallelism for Long Prompts on Multicore CPUs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19801 - Fantastic Metrics and How to Find Them: Meta-Evaluating Metrics for Multi-lingual Style-Personalized Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19166 - Manac\'a-1B-Instruct-2: Reproducible Safety Alignment for a Native Brazilian-Portuguese LLM. Negative DPO Results, a Controlled Composition Scan, and a Silent Failure Mode of the LLM Judge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20570 - Not All Criteria Matter: Importance-Aware Criteria Weighting for Rubric-Based LLM Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19915 - LintEval: Benchmarking LLMs on Linter-Guided File Refactoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20027 - Weighted Ensemble Sampling for Rare-Event Estimation in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19202 - J-tau: A Fully Localized Japanese Benchmark for Tool-Agent-User Interaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19638 - Hidden in Plain Sight: Advancing Harmful Content Understanding via Perception-Aware Adversarial Self-Play Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15449 - When Occupation-derived Skills Don't Help: On the Limits of Skill-Augmented Career Path Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20186 - What Does LALM Post-training Learn? Rethinking Audio Understanding and Reasoning Capabilities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19476 - Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.13546 - MasalBench: A Benchmark for Contextual and Cross-Cultural Understanding of Persian Proverbs in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22050 - Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20419 - Qwen-MT-Lumen at WMT2026: Instruction-Specialized Translation via Quality-Aware Training and On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19758 - The Sum of All Summaries: PROPALIGN for Graded Proposition Salience Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19387 - Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00578 - Dual-Evolving Reinforcement Learning for Automated Reward Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13399 - SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20431 - On Challenges in Evaluation Methodology: A Review Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25923 - From Efficiency to Sufficiency: The Cost-Aware Measurement Design Framework for Automated Essay Scoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19287 - MemDuet: Learning Dual-Process Memory for Long-Context Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19928 - LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12990 - GraphRAG-LTM: A Layered Threat Modeling Framework for Attacks on Graph Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19549 - PerSo: Investigating Facets of LLMs' Social Intelligence in Real-World Persuasion Scenarios Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20548 - Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18784 - Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28166 - What Is a Clarification? Estimating Model-Dependent Input Ambiguity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20052 - Fish Audio Drama 3 Technical Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18010 - When Can Digital Personas Reliably Approximate Human Survey Findings? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10659 - ChronoCulture: Evaluating Cultural Awareness Across Time in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20472 - CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19134 - Designing Textual Interfaces To Enhance Llm Reasoning On Audio-Visual Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20085 - Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25335 - Learning Perception to Action Rules through Reinforcement Learning for Theory-of-Mind Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19796 - Evaluating Large Language Models for Multilingual Abstractive Summarization: A Comprehensive Study of English and Bengali Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19003 - How Do LLMs Understand Legal Philosophy? Diagnosing Legal-Philosophical Reasoning in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19427 - TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26112 - ILM: An AI-Powered Storytelling Educational Tool Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12064 - Reviser: Writing and Editing Text with Autoregressive Cursor Actions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20830 - NEPSEE: A Double-Annotated Benchmark for Nepali Sentiment Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19190 - Crossing the Gender Binary: Modelling Gendered Reference in Science Fiction and General Fiction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19028 - Beyond Corrected Actions: Training LLM Agents on Textual Critiques Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19367 - A Strong Harness Narrows the Model Gap: A Comparative Evaluation for Legislative Document-to-XML Conversion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19999 - Anuvani-Diarization: Zero Shot Speaker Diarization and Annotation Conventions Across 22 Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20327 - Structure-Preserving Document-Level Data Augmentation via Discourse Parsing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19497 - MemoryAthena: Adaptive Routing over Latent and Generated Memories Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25853 - PERCEPT: A Corpus for POS Tagging and Analysis of Persian-English Code-Mixing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10109 - Eigen-Agent: Adaptive Multi-Agent Scientific Reasoning with Monitor-Based RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.21193 - Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02022 - One Block Ahead: Promoting Sampler State in Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19510 - Language Exposure Matters: Distribution and Order in Multilingual BabyLM Pre-training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20102 - When Reasoning Supervision Hurts: TTCW-Based Long-Form Literary Review Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.20364 - Evaluating LLMs as Agentic Workflow Executors in Real-World Customer Support Skills Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14346 - TreeSpark: Learning to Draft the Trees You Verify for Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20175 - MakSafe: A Spatiotemporal Semantic Framework for Formal Specification and Compliance Checking of Road Vehicle Safety Rules Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19735 - BTS-AgentBench: A Deterministic, Replayable Pipeline from Read-Only Telemetry Logs to Agent Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27334 - Off-the-Shelf Language-Vision Encoders Predict Human Gaze Preferences in Visual World Experiments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07282 - Frozen Memory Is Not Enough: Rethinking External Memory as Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17050 - LLMs Can Get "Brain Rot": A Pilot Study on Twitter/X Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.13928 - Likelihood Is Not Authorship: Can We Reliably Measure Human Contribution in AI-Assisted Writing? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19767 - Misinformation Propagation in Benign Multi-Agent Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16710 - Assessing and Refining ChatGPT's Performance in Identifying Targeting and Inappropriate Language: A Comparative Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.21710 - EGCForest: Structured Agent Memory Organization for Enterprise Group Chats Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19836 - Reward Design for Physical Reasoning in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13993 - FACES: Fine-grained Gated Semantic Alignment for Multimodal Emotional Support Conversation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20051 - HERO: Harnessing Evidence for Test-time Refinement and Prompt Optimization in Program Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19184 - Ouvia: A User-centered Framework for Measuring Usability of Speech Translation in Real-World Communication Scenarios Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06177 - SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17727 - Same Claim, Different Interpretations: How LLM Agents Resolve Ambiguity in Scientific Claims Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20457 - Read the Room Before Your Model Generates Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18820 - ANCHOR-RE: An Agentic Biomedical Relation Extraction Framework with Retrieval Augmentation and Error-Driven Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03154 - Does Machine Translation Retain Media Bias? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19945 - VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19361 - $\pi$-CoT: Prolog-Initialized Chain-of-Thought Prompting for Multi-Hop Question-Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.20642 - TreeFlex: Agents Navigating Their Own Search Trees Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.20334 - CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20272 - DUALVIEW: Leveraging Broad and Output-Specific Evidence for LLM-based Multi-Output Text Regression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19206 - When Is Enough Not Enough? Illusory Completion in Search Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.07549 - Back-Translation Still Matters: Leveraging Monolingual Data for Low-Resource Machine Translation with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18818 - Are We Really Measuring Forgetting? Pitfalls in Evaluating Machine Unlearning for Multimodal LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19613 - More Than Seeing: Vision as Scalable Anchors in Native Multimodal Pre-Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19443 - SoK: Grading Open-Text Legal Answers, from Law School Exams to Trustworthy Rubric Judges Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19992 - PA1-OPD: One-Step Prefix-Augmented On-Policy Distillation for Language Model Pretraining Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19601 - Beyond Benchmark Accuracy: A Diagnostic Test for LLM Chemical Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19906 - Gray-Box Hallucination Detection in LLMs with Token Identities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19996 - Hybrid Gated Attention Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11805 - Selective Reasoning for Typed Decision Models: When to Start, Read, and Stop Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19644 - Towards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19108 - Do AI Agents Gossip? Evaluative Talk in Human and AI-Agent Online Communities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20360 - MemeTrace: A Multimodal LLM-Based Agent for Safety-Aware Meme Provenance Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19267 - From Triage to Impact: A Multi-Hop Reasoning Benchmark for Explainable Persian Hate Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20370 - Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19723 - ConRAG: Consensus-Driven Evidence Flow for Multi-Hop Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28093 - ForkGRPO: Efficient Exploration and Fine-Grained Credit Assignment for Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19408 - ListQA: A Benchmark for Evaluating List-Formatted Factual Knowledge Retrieval in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19165 - Plant Memory: Technical Language Processing and a Verified Maintenance Ontology for Agent-Accessible Failure Knowledge from SAP PM Work Orders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19131 - Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.12553 - Cascaded Retrieval with Cross-Modal Query Refinement for Efficient Visual Document Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20367 - Can LLMs Access their World Knowledge for Event Prediction? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19021 - Measuring and Reducing Unusable Replies of LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19659 - Can LLM Agents Efficiently Identify Appliance Faults? Insights From Diagnosing a Simulated Appliance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19291 - DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17029 - Taking the PULSE of Medical Reasoning: Step-Level Retrieval Timing for Knowledge-Grounded Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20292 - PRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19762 - ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19388 - To Reason but Not to Stop: Understanding and Recovering Pruned Large Reasoning Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19934 - Geometric Alignment without Functional Equivalence: A Layer-wise Analysis of the Speech-Text Modality Gap Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01502 - RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19705 - REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19561 - Pre-Trained Language Models as Zero-Shot Tools for Social Science Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19048 - How to Build a Benchmark That Actually Measures Taste Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14707 - Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.18360 - Titan-Llama: Retrofitting Pre-trained LLMs with External Neural Memory Modules Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19210 - From Unreliable to Usable: Decomposing Failure Modes and Confidence Signals in LLM Entity Extraction - Evidence from Cyber Threat Intelligence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20417 - Reclaiming Low-Quality Instruction Data with Rule-Guided LLM Reconstruction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.23160 - Terminal Agents Suffice for Enterprise Automation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.00073 - HarnessSQL: Harness-Native Training for SQL Agents in Realistic Database Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12274 - Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15692 - Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13304 - PersEvalBench: Can LLM Evaluators Judge Contextually Appropriate Use of Persona Information? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19314 - EconCausal: A Context-Aware Economic Reasoning Benchmark for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.07231 - ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23069 - LLM-jp-4 Technical Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19331 - LLM-Based Policy Compliance Verification of Loan Applications Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20155 - Learning What to Keep: Transfer-Aware Personal Skill Learning from User Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19380 - BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16557 - Scaling Discovery Requires Forgetting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20563 - Neural POS Tagging for the Low-Resource Saraiki Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20279 - AVA-Encoder: Towards Agent-Native Video Representation Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12313 - Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19366 - How to Evaluate When You Don't Know How to Evaluate? Choosing Reliable Setups for Base Language Model Benchmarking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19185 - Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20067 - Vision-Language Models Integrate Conflicting Evidence Like Biased Bayesian Observers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19407 - What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20195 - Evaluating Compressed Memory: Dependence, Utility, and Content Benefit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19373 - AFCS: Atomic-Fact-Conditioned Synthesis for Factual Knowledge Pretraining Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20086 - Repairing Speech Access After Text Updates with Frozen Affine Fields Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20253 - Knowledge Distillation from Large Reasoning Models to Compact Student Models: A Case Study on the John O Bryan Mathematics Competition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31048 - Language Steering for Multilingual In-Context Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02326 - Joint Subspace Sparse Attention for Efficient Long-Context Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19026 - Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19741 - ANCHOR: Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16859 - Moral Combat: Exploiting Moral Foundations Theory to Jailbreak LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19587 - Learning Proposition-Level Links from Sentence-Level Supervision for Neuro-Symbolic NLI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15158 - GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19100 - Frustratingly Easy Majority Voting Using Length Conditioning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19890 - Scaling Multilingual Safety and Reasoning Evaluation through Reasoning-Guided Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20221 - ARCS: Towards Precise Text-to-SQL via Structured Disambiguation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09396 - Algorithmic Unverifiability of Safety for Fixed and Recursively Self-Improving Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28639 - REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16288 - Monte Carlo Estimation for KV Cache Eviction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07643 - RealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14397 - An Iterative LangGraph Agent for Text-to-SQL: Natural Language Access to the Chicago Crime Database Source: arxiv-cs-cl Topic: AI Research (+AI, PostgreSQL) URL: https://arxiv.org/abs/2609.22917 - Model vs. User: Whose Values Prevail? Inference-Time Value Alignment in Multi-Turn Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19817 - Review Rarely Beats the Stronger Model: Separating Verification from Capability Transfer in LLM Pipelines Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15897 - KoAGE: Do Large Language Models Know, Learn, and Coin Korean Neologisms? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19399 - OpenTWBench (Open Taiwan Benchmark): Taiwan-Domain Knowledge Evaluation for Large Language Models, and How the Measurement Apparatus Shapes the Score Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19848 - Evolve Together, Fall into Place: How Social Scaffolding Shapes Self-Evolving Multi-Agent Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19799 - AdaptFuse: Training-Free Sequential Preference Inference via Externalized Bayesian Computation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03925 - Whose Data, Whose Benchmark? A User-Centric Framework for Auditing Evaluation Resources Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19268 - BANGLAPLAN: A Benchmark for Constraint-Based Planning and Decision-Making in Bangla Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19704 - QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.08689 - Learning Reusable Agent Subroutines from Experience Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02994 - Do Syntax Heads Influence Model Behavior? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19231 - DivAlgo: A systematic evaluation of algorithmic diversity for code generation models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19157 - Qwenfant: Train Big Character-level BabyLMs on Concise Parallel Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19294 - MolLean: A Process-Verifiable Language for Chemical Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20459 - A large-scale pipeline for LLM-assisted corpus annotation: variation and change in the English consider construction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.12306 - Mitigating Video Hallucinations via Attention-Guided Representation Perturbation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19728 - Copy-Paste Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19247 - PLACID: Privacy-preserving Large language models for Acronym Clinical Inference and Disambiguation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23678 - MultiPartyTurnBench: Benchmarking Floor Control in Multi-Party Spoken Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20172 - Semantic Communities and Boundary-Spanning Lyrics in K-pop: A Graph-Based Unsupervised Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12881 - T2J-BENCH: Benchmarking Coding Agents on Execution-Grounded PyTorch-to-JAX Repository Migration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29054 - Rationale Distribution Distillation via Flow Matching for Distributional Continuous Latent Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19871 - Interlock: From Local Correctness to Task Completion in Long-Horizon Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19686 - CALM-IT: Enhancing Synthetic Motivational Interviewing Dialogue Quality with Conversational Dynamics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10085 - ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20503 - Latent Preference Modeling for Multi-Session Personalized Tool Calling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17886 - Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20461 - Last Secure Code Benchmark: Is the Code You Vibe Secure? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14766 - UDHRBench: Benchmarking Human Rights in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15179 - Integrating AIRL-Based Reward Estimation into a Control Method Using Fuzzy Inference and Policy Gradient Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14723 - Self-Representation Alignment in Diffusion Models for Video Background Music Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15575 - Cross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16050 - Beyond Gate Weights: Decision-Level Interpretation of Radiomics-Image Feature Fusion for RCC Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14152 - North or South? Diagnosing LLMs' Understanding of North Korean Language, Society, and Knowledge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15282 - Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14162 - SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17093 - GREAT-ESDD: Graph Edge Attention Network for Effectively Steered Delivery Decisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14792 - Configuring RAG Systems: What Breaks, Where Originates, and How to Fix Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18567 - Single-step Retrosynthesis via Reinforcement Learning from Forward Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15141 - Have You Been Convinced? A Neuro-symbolic Argumentation Reasoning Approach to Detecting Persuasiveness in ChangeMyView Discussions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15091 - Auditing LLM Program Search for Bermudan Stopping with Primal--Dual Certificates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14063 - When LLM Agents See a Conflict but Still Proceed: Cross-Domain Dependencies in Network Slicing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17118 - Learning to GUIDE the Group: Self-Learning LLM Facilitation Across Multi-Party Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16231 - Recurrent In-Context Learning for Tabular Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14998 - MedHarnessBench: A Unified Benchmark for Healthcare Agent Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15714 - VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.17057 - CESNET-TimeSeries26: A Multi-Year Network Traffic Time Series Dataset for Annual Seasonality, Concept Drift, and Long-Term Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14799 - Getting Space Right: Agentic Rewards for Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14852 - XAI-Guided Fourier Domain Generalisation for Pure-Simulation Sim-to-Real Deep Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16478 - A Node Embedding Framework for Model-Centric Conformance Checking in Process Mining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17702 - Continuous Risk-Based Scheduling for Food Safety Inspection: Integrating Historical Decay with Event-Driven Consumer Review Signals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15191 - RadixFlow: Filling Execution Bubbles in Prefix-Cached Hybrid LLM Serving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18143 - Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17816 - Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18606 - Upstream Influence, Downstream Re-Anchoring in LLM Agent Chains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17723 - Beyond Discrimination: Evaluating Probability Calibration in Radiomics-Image Fusion for Renal Cell Carcinoma Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14151 - Monitoring latent reasoning in looped language models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18127 - Suggested Is Not Superseded: A Pre-Registered Evaluation of a System-One Model as a Memory-Retirement Gate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15710 - AgentStripes: An Evidence-Graded Maturity Model for AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18603 - Executable Prefix Values for Locating Agent Failures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17633 - QORH: Learning Query-Specific Ordered Rule Hypergraphs for Inductive Knowledge Graph Link Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18198 - WeatherBridge: Forecast-Aware Multi-Source Input Adaptation for Pretrained Weather Forecasting Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14863 - Single-Sample Decoding of a Two-Layer Sound-Word Canvas Model for Thai Klon Pad Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14980 - Reels-RSI: Program-Level Self-Improvement for Code-Rendered Explainer Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14495 - The Future of AI-assisted Physics: Discovering, Verifying and Organizing Results via Formalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14059 - Predicting how model propensities generalize out of distribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14937 - AcrossVAM2.0: Conflict-Aware Point Supervision for Parameter-Efficient Video Diffusion Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14693 - PLDiv: Measuring Dataset Diversity and Semantic Collapse via Persistence Landscapes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14031 - Using Evidence-Centered Design to Guide Prompt Engineering in Measurement: An Illustration with Automated Essay Scoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15231 - Constructed regional photovoltaic generation fields improve ultra-short-term distributed solar forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16110 - TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17540 - LATCH: LLM-Assisted Timing Closure Harness for Post-Route FPGA Optimisation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16625 - Radioactive Feedback: Tracing Models Trained by Label-Only LLM Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15685 - Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.16895 - HarnessNet: Feedback-driven Hierarchical Joint Harness Evolution for Multi-agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15221 - RAN-JEPA: An Action-Conditioned World Model for Energy-efficient Mobile Network Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17584 - Overtaught, Underlearned: Learner-Centered Distillation from Multi-Agent Discussion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16543 - What Counts as the Same Task? Executable Contracts for Robustness Evaluation of Tool-Using Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14477 - How Should a Camera-First AI Agent Work? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14772 - Phantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16141 - Pick the Mixture, Not the Samples: Combinatorial Data Selection for LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14028 - Mitigating Cross-Modal Hallucinations by Correcting Modality Misrouting in Omnimodal LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18141 - Reliable Text-to-SQL in Resource-Constrained Settings with Small LLMs via Iterative Retry Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17305 - Releasing the Inner Jev: A Simple Recipe for Open Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17205 - Computational Reflective Equilibrium for Agentic AI: A Rawlsian Alignment Scaffold for Governance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16015 - Mixing Regularization for Average-Reward $Q$-Learning and $Q$-Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14988 - Cross-Lingual TTS for Indian Languages: A Benchmark and Inference-Time Duration Estimation Strategies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14826 - Delegating Earth science model calibration to knowledge-guided LLM agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18378 - KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14448 - Uncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16155 - Rethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18566 - Compositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14514 - GG-Nav: Goal-oriented Grounding Chain-of-Thought Elicits Reasoning in Navigation Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14541 - Two Routes to Interoceptive Prioritisation: Dissociating Likelihood Precision and Preference Reweighting in Active Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18617 - WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16927 - Self-improving data synthesis can scale embedding models across domains and tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14730 - Handoff Curves: Initial Selection, Later Handoff, and Supervision Targets in Multi-turn LLM Routing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15993 - Agent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15529 - GUIDE: Computationally Augmented Consensus for Trustworthy Clinical Practice Guidelines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16108 - Judges Follow the Reference: The Derivation Gap in Verifying Tool-Call Arguments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18497 - Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17860 - Humans vs. Machines: A Comparison With AI Agents in Software Reverse Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14960 - EPOCH: Coverage-Aware Evolution with Experiential Preference Optimization for LLM-based Automated Heuristic Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17379 - Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16261 - Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14146 - Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.14209 - The Sharp Directions Are Against You: Curvature Analysis of Activation Steering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16084 - MFG: Multi-turn Feedback Guided Molecular Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18851 - Physics-Informed State Space Models for Day-Ahead Photovoltaic Power Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14014 - OneShot: Label-Efficient Detector Weighting for Time Series Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16219 - Understanding Unified VLMs: From Attention Probing to Guidance Tuning for Multimodal Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15227 - EvolvAttack: Backdooring self Evolving VLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15244 - Specification-Based Testing of Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14443 - Revocation Is Not Complete at Receipt: An Executable Outcome Contract for Distributed Agent-Tool Gateways Source: arxiv-cs-ai Topic: AI Research (+AI, PostgreSQL) URL: https://arxiv.org/abs/2610.15991 - Neos: Learning to Interleave Search and Visual Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17043 - BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18780 - Rethinking Activation Functions: Reducing Bias Can Improve Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14500 - Agency as a New Organizing Abstraction for Computer Science Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17410 - Learning How to Remember: Memory Modality Selection for GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17928 - Transparent Information Flow Modeling for Role-Aware AI Act Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16916 - Deep Learning-based Semantic Segmentation of Dental Radiographs: Comparative Evaluation of PSPNet, DeepLabv3, UNet, and UNet++ Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15061 - Barycentric Anchored Weight Search for Robust Model Merging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14017 - Belief Embedding Tree Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15046 - Visible but Not Avoided: State-Dependent Re-Proposal of Rejected Candidates in Catalog-Based LLM Optimization Loops Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15738 - Limitations on Autoregressive Token Generation via Sequential Sampling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14615 - TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15093 - CondMSP: Condition-Informed and Resource-Aware Inorganic Materials Synthesis Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15603 - Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14913 - Embodied Zero-Shot Task Planning via Hardware-Aware LLM-VLM Integration for Grounded Robotic Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14106 - One Model, Multiple Compute Budgets: Multi-Ratio ConceptMoE for Flexible Compute Across Turns Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14074 - Transparency as Answerability: Role-Dependent Information Flow Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16887 - RetryBench: Separating Retry Permission from Recovery Outcomes in GPT Tool Use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15884 - Do you "see" what I "see"? A Multi-panel Visual Question Answer Dataset for Large Language Model Chart Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14173 - Can You Trust Your Preference Models? Stackelberg Games for Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15008 - Framework for an AI-Ready ARPES Community Database Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15236 - WorkBorne: Discovering Agentic Tasks from Real-World Artifact Transitions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14915 - Efficient Multi-Agent Reasoning via Confidence-Guided Adaptive Debate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16343 - Large Language Model Assisted Transportation Planning through a Differentiable User Equilibrium Layer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16140 - Beyond Black Boxes: Visual Grounding for Text Embeddings Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.18047 - Double-Rollout Reinforcement Learning with Sampling-based Reward Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16593 - GesBench: When and Where Do Multimodal Language Models Perceive Social Meaning? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15129 - PreSO: Privileged Representation Isolation for On-Policy Self-Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14001 - AI Discovery in Combinatorics: From Problems to Solutions and Back to Bigger Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16555 - G$^2$WAM: World Action Models for Efficient and Geometry Grounded Image-Goal Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16558 - Size Generalization for Diffusion Routing Solvers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17192 - Select or Rewrite: Oracle-Guided Fine-Tuning for Generative ASR Post-Editing from N-Best Hypotheses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15056 - PEAM: On-device Communication Agent for Personalized, Efficient and Autonomous Mobile Network Configuration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14855 - Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14190 - Memory Echo in Single-Agent Long-Term Memory: Lifecycle Evaluation and Provenance-Guided Mitigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17763 - The RNN Homunculus: Learning to Gate Long-Term Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14279 - Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16552 - Autonomous 3D Visual-Thermal Inspection for Utility-Scale Solar Farms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17762 - WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18067 - Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14428 - Compare to Correct: Pairwise-Guided Logit Adjustment for LLM Test-Time Scaling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18583 - Certify the Decision, Not Every Score: Exact Top-k Selection from Few Evaluations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14996 - Fitting Every Hint Is Not Enough: Premature Floods in Recurrent Algorithmic Reasoners Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14982 - A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14041 - Reference Wording Shapes Retrieval of Robot Task Instructions Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.17549 - Trust Hinders Bidirectional Human-AI Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15136 - Does a Hosted Decision Model Respect Irrelevant Alternatives? A Pre-Registered Test of Option-Set Dependence in Jev Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16655 - CHEAR: Confusion-Hierarchy Evidence-Aware Reasoning for Cost-Efficient Human Activity Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15298 - SLS-Bench: A Benchmark for Incident Log Summarization with Synthetic Observability Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16412 - State Representation Shapes Long-Horizon Agent Learning and Transfer: An Empirical Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15407 - Unconstrained CTI-REALM with Open-Weights Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14180 - HGA-Quant: Heterogeneity-Aware Quantization for AutoRegressive Visual Generation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15297 - Does the Explanation Drift Before the Guarantee? Label-Free Early Warning on Evolving Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16534 - SAGE: Efficient Protected Vision-Language Inference on Smart Glasses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14089 - Knowledge transfer between simple discrete worlds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15081 - Artificiality's First Exam: An LLM-Referenced C-test for Supraintelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14005 - Think in Strategies, Act with Tools: Traceable Agentic Optimization for Combinatorial Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14736 - ECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17869 - Scalable Robust MCTS with Anytime Deterministic Optimality Guarantees Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15461 - Interactive 4D Volumetric Liquid Forecasting under Moving-Solid Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16167 - Sequent-Prover: Training Agents for Formal, Checkable SMT-based Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15258 - Large Language Models Extend Known Research But Do Not Create New Research Directions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17439 - Fresh at Decision, Stale at Action: Routing New Information to LLM Decisions Already Made Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18126 - Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15218 - LYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14777 - Joint Discrete and SE(3) Diffusion for Protein Interface Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14699 - Consider, Then Choose: Order-Invariant Decisions in System One Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18233 - ADAPT: Audio-Depth Action Planning with Transition-Aware Rewards for Lights-Out Industrial Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15956 - MCPDisCo: Seesaw-Mitigated Tuning for MCP-Native Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14956 - AegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14643 - CoverSynth: Coverage-Guided Generation of Retrieval Evaluation Sets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15409 - Equal-information evaluation of credit assignment in modular financial reinforcement learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14750 - An FPGA-Based Spiking Neural Network for Spatiotemporal Pattern Learning and Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17463 - Jeva: System One Models from First Principles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18773 - AM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18090 - Probabilistic Multi-Source Data Selection via Learnable Categorical Priors: Variance Reduction and Guaranteed Derandomization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14942 - What Makes a Latent Space Shared? Direct and Recoverable Compatibility in Motion VAEs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17376 - Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14605 - Stable Token-level Scheduling for Serverless LLM Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17689 - Anchor-and-Harvest Curriculum: A Fully Unmasked Non-LLM Curriculum for Craftax Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15328 - Predict Before You Modify: Learning Improvement Dynamics for Self-Evolving Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13991 - AI-Native Product Management: A Vision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14823 - SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14745 - SemTree: Judge-Aware Semantic Decision Trees for Inspectable and Repairable Rule Decisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13999 - When 1+1 Backfires: Rethinking Relevance-Diversity Balancing for Sample-Aware Visual Token Reduction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16615 - MADDIE: Multi-Agent Drug Discovery Engine Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16975 - EvoQuantLab: Training-Free Dual-Loop Evolution for Auditable Quantitative Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17130 - PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17900 - Get In, Decide, Prove: A Merchant-Side Readiness Benchmark for Agentic Commerce Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17378 - Who to Trust in Multi-Robot Systems: Joint Robot and Object Hypothesis Trust Inference via Neural-Symbolic Cross-Validation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14530 - Memory-Efficient Integer-Only Training of Deep Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16298 - When Log Parsing Removes What Matters: Detecting Failures in Distributed GPU Workloads Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14009 - PopGen: Generating Semantically Diverse Populations for Zero-Shot Coordination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15969 - Coarse-Graining Recursive Expert Computation: Continuation-Relative Interfaces and Failure Modes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14413 - Coding LLMs Can Be Harnessed to Learn Interpretable Models from Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14006 - Actionable Meta-Requirements for AI Robustness Auditing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14356 - VH-GPO: Verified Handoff for LLM Agent Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14000 - Correction Training for Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14136 - RoboHarness: A Simple Harness Outperforms VLA and World Actions Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14018 - Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14389 - CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18095 - ScreenASR-Bench: A Tiered Benchmark for Speech Recognition with Visual Context Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16260 - RASSG: Repair-Aware Semantic Survival Gating for Streaming Tool Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14659 - Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18449 - Comparative Study of Canvas- and Coordinate-Based Geometry-Conditioned Neural Networks for Real-Time Prediction of Indoor Environments with Varying Room Dimensions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15885 - ASIWorld: Benchmarking Autonomous Agents in a Persistent Survival Sandbox Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14807 - OpenDepth: Repurposing Image Editing Priors for Robust Open-World Monocular Depth Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17610 - When Goals Leak Across Relationships: How Cached Goal Representations Shape Cross-Client Decisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17365 - LabInstruct: Benchmarking Situated Instructional Video Generation for Lab Procedures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14020 - Agentic4PDM: Host-Governed Evidence Admissibility for Industrial Fault Diagnosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17786 - LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18092 - Accuracy and Uncertainty in Machine Deception Detection (Research White Paper) Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15314 - Harness^2: Recursive Agent Harnessing for an Open World Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14224 - CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14763 - ANASSA: From High-Level Framework to Low-Level Architecture for Spatial Agentic AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14382 - The Silent Failures in Agentic Data Science Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14115 - Subgraph-Aware Training of Language Models for Knowledge Graph Completion Using Structure-Aware Contrastive Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.12703 - Prospective Forcing: Learning to Look Ahead for Autoregressive Long Video Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14654 - When Skills Remain But Access Fails: Factorized Skill Memory for Continual Skill Internalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15492 - VETNET: Assembling Benchmark Datasets for AI-Driven Veterinary Innovation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14149 - MARL-BattleGrounds: A Novel JAX-native Benchmark for Heterogeneous and Competitive Multi-agent RL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14883 - Large Decision Models: Repurposing Large Language Models as Single-Pass Decision Makers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15501 - ChemExplain: A Multimodal Benchmark for Explanatory Chemical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17183 - Is the Future Predictable? Modeling Future Predictability for Reliable Temporal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14073 - MemeLogos: Knowledge-Driven Retrieval-Augmented Reasoning for Harmful Meme Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15463 - EmoXpt: Analyzing Emotional Variances in Human Comments and LLM-Generated Responses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.06597 - AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18860 - Reasoning for Propaganda Detection via Label-Guided CoT Optimisation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17271 - Towards Merging-conditional Backdoor Unalignment against Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14701 - Big-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15634 - Pollard: Governed Semantic Execution Trees for Framework-Independent AI Agent Control and Replay Source: arxiv-cs-ai Topic: AI Research (+AI, PostgreSQL) URL: https://arxiv.org/abs/2610.16145 - MontageFlow: Physically Valid High Fidelity EEG Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14507 - Auditing Future-Memory Use in Point-in-Time Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18602 - ClinEdge: An Expert-Graded Benchmark of Real Patient Edge Cases Where Frontier Multimodal Models Fail Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15239 - Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14705 - Diffusion-Based Auctions for Multi-Winner Banner Ads Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14473 - Generalizable field of view extension for diffusion MRI via conditional flow matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17401 - Structural Baselines Matter for Agent Failure Detection and Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16661 - Coupled Harness--Model Evolution for Scientific Equation Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17740 - Target-ESS Tempered Policy Optimization (TETPO): Smooth Variance Control via Bridge Importance Sampling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14440 - ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18355 - ChronoScribe: Semantic-Numerical Specialization for Instruction-Driven Time Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16345 - Safety for Whom? Benchmarking Understanding Beyond Refusal in Egocentric Multimodal Assistants Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17728 - Heterogeneous Agentic Coevolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16078 - Who Improves the Robot? Toward Physical Recursive Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18842 - Understanding Personalization Gains in Whisper Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17019 - Complex materials engineering via Provenance Action Graphs: potential, structure and demonstration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18314 - InCLAD: A Continual Learning Benchmark for Industrial Visual Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15032 - Memory Without Curation: Learning Multi-Stream Latent Memory for Robot Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14406 - Choosing LLMs for Strategic Agent Interactions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18354 - Beyond Single-Pathogen Forecasts: Predicting Shared Respiratory Hospital Burden from Influenza, COVID-19, and RSV Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16074 - Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14790 - Geospatial Vector Geometry as a Native Spatial Modality for Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16769 - From Stages to States: Unified Iterative Reasoning for MLLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15620 - Unlocking Token Rewards via Training-Free Reward Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18704 - Counterfactual Rollouts for Offline Contrastive Goal-Conditioned Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14953 - Protein Crystallization Segmentation and Classification Using Subordinate Color Channel in Fluorescence Microscopy Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15286 - VLCQ: Post-training quantization for deep neural networks using variable length coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15092 - Chain of Thought Monitoring Can Fail Even When CoT Is Necessary Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18105 - ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17718 - Deep learning from a control vantage point Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14385 - Contrastive Covariance Subspaces for Activation Steering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14025 - Showing versus Doing: Teaching by Demonstration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14004 - Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15343 - FDE-Bench: Evaluating End-to-End Delivery from Underspecified Real-World Business Requests Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14539 - FON: A Draft-Revise Dual-Organ Language Model without Sequence-Level Quadratic Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16301 - Recall What Is Missing: Composing Evidence from Long-Term Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15642 - Chain Dimension Scaling: Communication-Efficient Loop-Style Scaling for Industrial Short-Video Ranking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16415 - SocraticRepair: Planning-Guided Socratic Tutoring for Program Debugging and Misconception Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15204 - Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17757 - On the Complexity Gap Between POMDPs and Multi-Environment POMDPs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15010 - Fewer Bits, More Tries: Recovering Capability Under Memory Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15372 - MHWA: Multi-timescale Hierarchical World-Action Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14727 - CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation Objectives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16876 - DexCast: Learning Real-World Dexterous Control from Human Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14691 - From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14625 - Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15150 - EarthAlign: Learning Language-Aligned Representations of Earth System Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14624 - DexFLEX: Contact-Aware Foundation Controller for Command-Guided Dexterity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14372 - GeoBridge: Evolving Transferable Decoder Topologies for Geometric Vision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15280 - PXRD-Bench: How Close Are We to Determining Crystal Structures from Powder Diffraction? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16480 - Benchmarking Quantum Kernel SVMs for Credit Card Fraud Detection: Performance Realities Under NISQ Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17027 - EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16523 - Beyond Successful Play: Diagnosing Opponent Modeling in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17310 - PRAISE: A Reproducible Workflow for Non-Programmer Scientists to Implement Published AI Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16980 - Bias Robustness of Genetic Multi-Criteria Sorting versus Learned Rankers under Proxy Skew and Label Contamination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14015 - GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13995 - ClawLoop: Self-Improving Agents via Harness-Native Training Loop Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14118 - Structural Chain-of-Thought: Reasoning with Executable Computational Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15107 - Weak Segmentation-Guided GAN for~Realistic Color Edition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16620 - Vela: User Behavior as Supervision Sparks LLM Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14709 - RL Post-Training Diffusion Language Models Along Their Own Generation Paths Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17266 - Boosting the Learning for Ranking Patterns Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16511 - SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18025 - One-Sided Verification Under Limited Expert Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18089 - Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14465 - Trace-to-Architecture: Capability Bottleneck Diagnosis for Harness Revision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16725 - Co-DSL: Human-LLM Co-design of Reusable Spatial Concepts for Layout Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15290 - Beyond the Verdict: Agentic Code Judging with Verifiable Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18760 - Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16312 - Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14542 - The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17158 - The Smart Buildings Challenge: Learning Foundation Models for Real-World Optimization at Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18511 - VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14939 - Reinforcement Learning from Real-Robot Interaction without High-Quality State Estimates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14042 - Rotate the Loop: Blockwise Conformality for Looped Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14030 - Small but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15964 - Vision: "What Don't I Know About User's Preferences?" How Uncertainty Estimation Improves Proactive Assistant Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15948 - PhysCodeGym: Benchmarking Coding Agents for Physically Verifiable 4D Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17288 - Learnable Low-Rank Polynomial Sketch for Effective Linear Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14219 - Towards Resilience: Slice-Driven Orchestration of Mobile IoMT in 6G-Edge-Continuum Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17296 - World Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16365 - TRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16333 - Prior-Fitted and Frozen Scorers for Multimodal Contrastive Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14770 - Beyond Bias Scores: Answerability Confounds in Activation Steering with Gradient-Constrained Direction Design (GCD) Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17641 - TRACE: Temporal Risk Assessment and Concept Editing for Safer Language Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15365 - ProgAgent: Learning Tool Orchestration through Programmatic Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14774 - ShellElastic: Scalable Elastic Pretraining with Simultaneous Maximal Updates and Hyperparameter Transfer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15124 - Analyzing the Dynamics of WSBM-based Echo State Networks using InputDSA Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15380 - When Pleasing the User Compromises Care: AI Sycophancy in Caregiver-Mediated Healthcare Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14360 - Verifier-Harness Co-Evolution for Training-Free Self-Improvement on Open-Ended Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17609 - HiPPT: Physiology-Grounded Wearable PPG Representation Learning via Multi-Scope Text Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14489 - Self-Evolving Agent Harness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18813 - EvoCowork: A Benchmark for Real-World Office Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14828 - Encounter-Driven City-Scale Human Mobility Generation with Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17672 - LLM Agents for Automated Post-Training via Structured Recipe Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18572 - SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15708 - Active Neural Matter: A Finite-Window Response Framework for Physical Systems and Distributed AI Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14549 - The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17301 - Imitation Holds a Key to Evolution: Localized Repair and Verified Skill Acquisition for Adaptive Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16125 - AuthGateBench: Benchmarking LLMs as Authorization Gate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16426 - Jevolution: A Framework for Studying Communication and Collective Dynamics in AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14449 - Words to World: Benchmarking LLMs in Interactive Physical Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15228 - PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14636 - Audit tools of the trade: Automated Auditor Elicitation Can Be Sensitive to the Context the Auditor Is Given Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16911 - Engram Injection: A Study of Temporal Validity in Parametric Language-Model Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15882 - Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18240 - Do Theorem Provers Need Theorem-Proving Agents? mini-Lean-agent: A Coding-Agent Baseline for Lean Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17331 - Exposing AI Inference as a Telco Network API over the 5G User Plane Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15062 - ConicFlow: constrained Inference-time optimal control for flow matching models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14307 - GeoFix: Geometry Fixing for 4D Consistent Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14293 - Energy Ring: Stabilizing Feature Energy for Reliable Test-Time Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14525 - ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16175 - Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17893 - A Self-Defining Operator for Distributed Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14547 - Beyond Outcome Feedback: Trajectory-Quality-Guided Experience-based Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14877 - SkillFusion: Towards Reliable Multi-Skill Composition for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15481 - YOUDrive: Driving Style as a Composable Direction for End-to-End Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14802 - RECAP: Calibrating Low-Bit Reasoning Models on the History They Read Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15259 - Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16117 - Budgeted KV-Cache Repair for Evolving Contexts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17338 - TraceSampler: Making Sampling Errors Predictable and Correctable for Accelerated Generative Sampling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14332 - Probable but Not Valid: A Psychometric Audit of Decision Models as Synthetic Survey Respondents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14912 - LIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16782 - Pre-Registered Genesis Accounting for Recursive Self-Improvement: First Audited Operator-Genesis Events in a Physics-Discovery Runtime Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14843 - Evidence-First Agentic Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17724 - RIECNN: Real-Time Image Enhanced CNN for Traffic Sign Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15127 - Agentic Data Engineering for LLMs: System Design and a Controlled Empirical Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14238 - SchemaWeaver: Accelerating On-Device Mobile Agentic AI via Schema-Guided Parallel LLM Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17436 - LLM-based User-Product Relevance Evaluation for Dynamic Product Advertising Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14550 - Akule: Fast and Scalable Multi-Robot Motion Planning via Sparse Interaction Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14248 - RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17665 - SceneForesee: Learning Scene Evolution for Spatiotemporal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14439 - ScienceBuddy-PV: A Verifier-Governed Recursive Improvement Protocol for Panvascular Intervention Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14523 - SAT-RL: Training Language Models for Logical Reasoning with Symbolic Solvers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14402 - OntoAR-HAR: Ontology-Guided Agentic RAG with Personalized Memory for Human Activity Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15292 - Neural Bayesian Networks for Modular and Scalable Decision-Making Under Uncertainty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16902 - Echo: Error-Compensated 4-Bit Tensor-Parallel Communication for LLM Training and Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14277 - Iterate on an LLM, Serve on an SLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14576 - Trace Evolution Bench: Measuring Whether Agents Improve from Their Own Environment Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15055 - PTGPO: Prefix Tree Group Policy Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14737 - Game-Creation-Agents: Autonomous Game Production Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16776 - A Reference Architecture for Integrating Agentic AI into Enterprise Software: Responsibilities, Interactions, and Variability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14818 - agent-risk: Risk Assessment for Changes to AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16280 - Understanding Gene Expression-to-Image Learning: Spatial Structure and Information Fidelity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17699 - Acceptable Misalignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16881 - Enhanced Trading Systems with Intelligent Market Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13998 - Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15207 - Posterior Flow Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13994 - A dataset of formalised theorem statements from the Annals of Mathematics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18301 - The Anatomy of a Blind Spot: What an LLM Judge Must Be Shown, and How Much Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15938 - Glasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16998 - Selective Knowledge Control for Continual GUI Agent Learning over Application Streams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06530 - Controllable Diverse Sampling through Pullback Directions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14294 - CAPTOR: a vision-language foundation model for Chest-Abdomen-Pelvis Oncologic CT Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14226 - EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16402 - FleetPilot: Fine-Grained Steering Empowers Real-World LLM Personalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14970 - Queue-Aware Token Communications: Bridging AI Representation and Wireless Service Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16730 - ZOIF: Zeroth-Order Influence Function Estimation for LLM Data Selection Using Only Forward Passes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15336 - Multi-Horizon Explainable Queue Forecasting and Resource-Aware Decision Support for Intelligent Border Control Using LightGBM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15930 - Self-Evolving Visual Agent via Margin Reward Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15084 - Keep Your Receipts: Trustworthy Cleanup of Agent-Built Knowledge Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17719 - Knowing the User Is Not Knowing What We Established: Grounding Awareness in Personal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18684 - Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15153 - Latent Algorithmic Structure Precedes Grokking: A Mechanistic Study of ReLU MLPs on Modular Arithmetic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23784 - Relational Semantic Grounding for Test-Time Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14721 - Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16838 - Seamless Deployment of Machine Learning Inference at the Far Edge: An Empirical AWS IoT Greengrass Architecture for Industrial Predictive Maintenance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14815 - EV-JEPA: Elastic V-JEPA for Any Device and Cross-Device Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14324 - Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15788 - scHFBiMamba: a bidirectional Mamba autoencoder for cardiac disease-state classification from single-nucleus RNA-seq data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15117 - Learning after Execution with Action-Specific Credit Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14573 - What Survives When Activation Steering Is Used as Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14958 - Toward System One Clinical Intelligence: Parameter-Efficient Fine-Tuning and Counterfactual Explainability of Decision Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15029 - AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18083 - When a Conceptor Complement Becomes Gain: Operator Geometry and Behavioral Attribution in Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16325 - Google Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15750 - ReTerm: Recovery Training for Self-Improving Terminal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18484 - To Defer or Not to Defer? Online Learning with LLMs and Congested Experts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15128 - The Singularity Has a Distribution: Exact Timing Laws and Detection Limits for a Stochastic Intelligence Explosion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18445 - PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15208 - Neuro-Symbolic Graph Transformers for Hierarchical Intention Recognition from Multimodal Human Activity Sequences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18176 - Knowledge Interaction in Hypernetwork-based Continual Learning: Conflict and Composition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15677 - MultiFlow: Vision-Driven Multimodal fMRI Encoding via Stimulus-Informed Source Flow Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15339 - DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17738 - Correct Choices, Failed Sequences: Choice2Seq Benchmarks Correctness Retention Across Output Interfaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16191 - Inverse Garment Design with Visual Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15582 - Efficient Safety Guardrails through Latent Dual-Hypothesis Reasoning with On-Demand Trace Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18304 - FARL: A Fully Automated Pipeline of RL Interface and Solver Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15691 - Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14334 - A Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15403 - RUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Can Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14299 - RetroPlanner: Multi-Route Expansion and Multi-Objective Reasoning for LLM-Based Retrosynthesis Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16391 - Splicing Hints into Reasoning Traces: Learning from Demonstrator Failures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13996 - Recursive Environment Scaling for General Long-Horizon Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16397 - PatientWM: Towards Generalizable Clinical World Models via Unified Patient States Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17059 - When Should Enterprise Policy Decisions Be Learned, and When Should They Be Reasoned? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17643 - ReTAC: Residual Test-Time Agentic Computation for Video Spatial Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16315 - CB-Agent: Concept-Based In-Context Learning for Sequential Action Selection Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.14574 - LASER: Defeasible Certificate Search for Long-Range Protocol Dependencies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14552 - Separating Prompt Harmfulness from Interaction Safety via Partial Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16761 - RES-MR: Risk-Aware Reasoning for Explainable and Safe Medication Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14474 - Scale, Drivers, and Limits of Representational Alignment Across Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14476 - ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14381 - UltraBERT: Beyond the Limit of BERT Pre-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15028 - REA: From Correct LLM Judgments to Safe Decision Delivery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17473 - CoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14021 - Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17827 - MRFlow: Mechanism-Structured Residual Flow Matching for Virtual Cell Perturbation Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13966 - Too Late to Prune: Generative AI, the Screen, and Team Creative Decisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14984 - Understanding and Reducing Misalignment in Persuasion Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16070 - Loose Lips: Understanding Privacy Leakage in Agentic Dialogue Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14071 - Back to the Future: Reverse-Consequence Modeling for Long-Horizon Particle Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18168 - SpecFit: Not All Draft Tokens Cost the Same in Offloaded MoE Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15417 - Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14216 - SkillForgeBench: Evaluating Agent Reliability Grounded in Agent Skill Specifications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14918 - Does a Governed Confidence Score Know When a Text-to-SQL Answer Is Right? An Exploratory Study on BIRD and a Pre-registered Confirmation on Spider Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17256 - Seeing Depth but Choosing Cues in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17976 - IsoVRBench: Video Reward Modeling Without Human Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17234 - Input-Conditioned Search for Efficient Test-Time Scaling of Recursive Reasoners Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18547 - WisdomNet: trustable machine learning toward error-free classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15299 - Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18579 - Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17840 - Can We Trust This Evaluation? Instance-Level Reliability of LLM-as-a-Judge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14029 - DSABench: Benchmarking Source Discovery, Coordination, and Execution for Multi-Database Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14700 - Data Portability Revisited: Toward the Human-Centric, AI-Driven Data Ecosystems of Tomorrow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15503 - HyWe: Unifying Search and Operation for Real-World Hybrid Web Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16319 - OPMD: On-Policy Mechanism Distillation Beyond Output Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14022 - MedEvo: Medical Reasoning Evolution through Knowledge Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17690 - SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14966 - SharedSAE: a unified sparse dictionary across u-net blocks and denoising time for diffusion models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13997 - Passing Tests, Missing Semantics: Evidence of Interpretive Lock-In in Plan-Based DataFrame Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15797 - History Replays Itself: Unleashing Long-Context Capability in Linear Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15715 - PsyMemBehav: Psychology-Informed and Memory-Grounded Two-Level Identity-to-Action Reasoning for Social-Media Behavior Simulation Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.14570 - AphaVoice: Text-to-Speech Model for Aphasia Patient Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14479 - Learning Perceptual Geometry of Natural Odor Mixtures from LLM-Derived Descriptors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17164 - When and How Order-Flow Interventions Work After Dealers Adapt Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18158 - StimFlow: Synthesizing Brain Activity from Images via Stimulus-conditioned Flow Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15341 - LURE: a Phase-Labelled Synthetic Corpus of Online-Grooming Exchanges Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15908 - MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17613 - Order-Consistent Latent Geometry for Reliable Short-Horizon Planning in World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18570 - Cowork-Gym: Synthesizing Interactive Work Environments at Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17670 - AlignPoison: Conditional Targeted Poisoning of Generative Recommenders via Decoding-Aligned Prefixes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14487 - Two-Stage Multi-modal Learning for Dynamic Audio-Visual Navigation: From Physical Alignment to Scene Aggregation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14077 - RAP-WAM: Learning World-Action Models through Predictive Rehearsal and Action Perturbations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16443 - Dependency, Compression, and Synergy: A Unified Information-Theoretic View of Multimodal Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14421 - Adaptive-Group Process Rewards for GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17710 - AssetForge: Asset-Augmented Task Synthesis for Business Automation Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18330 - Learning to Play: Reinforcement Learning and Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17391 - LeHami: Symplectic Latent Dynamics for World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15267 - Shaping Latent Mixture-of-Experts: From Expert Geometry to Layerwise Capacity Allocation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14644 - Visualizing the World Model in an Agent's Value Function Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14186 - AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14697 - Latent World Action Model for GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14228 - Lost in Implicit Routing: How LLM Agents Fail to Load Relevant Skills at Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18522 - Training a Compact, Strong, and Realistic Text-to-Speech Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14776 - Output Discipline Sets the Floor: A Falsification-Guided, Model-Agnostic Agent Protocol for Auditable Hypothesis-Driven Decision Making Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18298 - GAMW: Generation-Aware Mel-Domain Watermarking for TTS Traceability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15082 - Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18447 - MoMaTune: Model, Match, Then Tune Language Models for Numerical Records Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15235 - Label-Centric Knowledge Retrieval for Zero-Shot Text Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16182 - What Can Language Models Inherit from Solomonoff Induction? Limits, Attainable Properties, and What Served Conditionals Reveal Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14007 - Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18614 - A Hybrid Kinematic GCN and Elastic Transformer for Efficient Indian Sign Language Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14680 - Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18052 - Depth-progressive 3D seismic velocity model building via 2D generative diffusion models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14812 - AutoMARS: Automatic and Scalable Multi-Agent Large Language Model Framework for Supply Chain Risk Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17206 - Attention Sinks in VLMs Are Borrowed, Not Seen Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15855 - To Align or Not To Align: Check Your COMPASS Before You Train Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18638 - GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14754 - Large language model-generated patterns for epidemiological modeling: a multi-benchmark evaluation framework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15994 - Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17659