TILens Daily Edition 2026-10-27 Filters: topic=ai-research, github=hidden Stats: 1145 articles, 7 sources, 1142 research papers Top topics: AI, AI Research, Information Retrieval ## News - 😺 OpenAI's big day brought a disproof and Terra Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/openai-s-big-day-brought-a-disproof-and-terra/ - OpenAI Cuts Terra’s API Prices in Half as Safety Tests Expose Authorization Risks Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/openai-gpt-6-1-terra-api-price-cuts-authorization-risks/ - OpenAI Reports Three AI Discoveries. How Will Scientists Verify Them? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/can-scientists-keep-up-openai-ai-generated-discoveries/ ## Research - The sleep framework: A new way for LLMs to retain knowledge in continual learning Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/the-sleep-framework-a-new-way-for-llms-to-retain-knowledge-in-continual-learning/ - An AI Agent Can Spot a Mistake and Still Not Fix It Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/i-broke-a-browser-agent-on-purpose-spotting-the-fault-was-not-the-same-as-fixing-it/ - Who Watches the AI? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/who-watches-the-ai/ - In the Age of Borrowed Thinking, How To Become More Valuable as AI Gets Smarter Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/in-the-age-of-borrowed-thinking-how-to-become-more-valuable-as-ai-gets-smarter/ - Developers Felt 20% Faster With AI. They Were 19% Slower. Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/developers-felt-20-faster-with-ai-they-were-19-slower/ - LoCA: Enabling Multi-Modality in Geospatial Location Encoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32894 - WADE: An LSTM-Based Anomaly Detection Engine for WebAssembly Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31984 - Towards Trustworthy AI-Enabled Emergency Medical Dispatch: Uncertainty-Aware Ambulance Travel Time Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31944 - Residual Calibration via Local Feature-Space Refinement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30652 - TileShare: Training-Free Acceleration of Overlapping Tiled ViT Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32233 - Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06474 - MLIPS: Multi-Layer Indexer Pool Sharing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27438 - Heterogeneous Agent Collaborative Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02604 - Watermarking Should Be Treated as a Monitoring Primitive Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13095 - GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05369 - RoboCode: Learning Reusable Action Primitives for Robot Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32225 - The Value of System 1 Models in Medicine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31315 - Deep Learning-Based Prediction of HER2 Status from Whole-Brain MRI in Breast Cancer Brain Metastases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32774 - ZENO: Nonlinear filtering with Zakai Equation Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32926 - Score-Preserving Continual Lasso under Task Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32708 - Instance-dependent Stochastic Lipschitz bandit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29748 - Putting Transformer Theories to the Test Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32104 - A curated multi-endpoint drug-protein bioactivity dataset with construct-aware protein targets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32490 - Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32195 - Regularised RL improves sim-to-real transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32855 - State Estimation as In-context Tabular Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32487 - A Mathematical Theory of the Jacobian Lens Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31955 - Universal neural network approximation of symmetric polyconvex energies and envelopes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32598 - Deep Learning Warm Starts for Trajectory Optimization on the International Space Station Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.05588 - SemantEq: Faithful Bidirectional Equivalence of Formal Statements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32919 - Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07910 - On the Complexity of Best-Arm Identification in Non-Stationary Linear Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.10346 - BiLoCo: Binary Low-Rank Corrections for Post-Training Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32243 - The Role of Quantum in Hybrid Quantum-Classical Neural Networks: An Empirical Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04732 - Attractive Faces Skew Text-to-Image Reward Models and Leaderboards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28195 - Latent-Space Importance Weighting under Covariate Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15571 - Sparsity-driven emergence of functional modularity in multitask neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32153 - Fooling LLM Safety Guards into Judging the Wrong Text Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31695 - RADIANT: Object-Centric Feed-Forward Global Illumination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32075 - Compatible Likelihoods for Flow Matching on Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31981 - 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 - CodeJeNN: A simple C++ neural network generator for physics applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02746 - PlayerEmbed: Learning Behavioral Fingerprint Representations from Raw Input Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32727 - PROVE: Probabilistic Visual Grounding via Patch-Level Evidence for Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32440 - SEVI: Safe Evidential Real-World Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31829 - Every Weight Is a Path of Shared Discrete Decisions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31931 - Quantum-aware Transformer model for state classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.21055 - Real-to-Sim Calibration of Bosch Etching Simulators with Few-Shot XSEM Data and Hybrid Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31904 - Driving Video Retrieval for Complex Queries with Structured Grounding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09109 - Where Rounding Happens Matters: Rounding-Location Alignment Stabilizes LLM Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32951 - The Price of Current-Effect Inference in Nonstationary Multi-Armed Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29982 - On the Runway Cascade of Transformers for Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2601.14522 - Dual-Adaptive Z-Score PPO: Dynamic Clipping Using Action Confidence and Normalized Advantage Magnitude Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32194 - Temporal Fair Division in Multi-Agent Systems: From Precise Alternation Metrics to Scalable Coordination Proxies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14879 - NodeSyn: Socially Aligned Synthetic Data for AI Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14381 - MAGIC: Margin-gated Contrastive Debiasing with Evidence Restoration for VLM Test-time Robustness Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32013 - EMG Tokenization Preserves Movement Information at a Fraction of the Bitrate Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32674 - SAUSS: Stochastic Approximation with Unbiased Simulated Scores for Limited Dependent Variable Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25304 - SpectrumQuant: Spectrum Alignment for LLM Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20303 - ReLEAP: Upcycling Vision Datasets through Cross-Task Unification and Semi-Supervised Annotation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32289 - Lean Finder V2: Semantic Search for Mathlib That Disambiguates User Queries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30843 - VETTA: Coordinating Turn- and Token-Level Credit Assignment for Multi-Turn LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08402 - ENCL: Enabling Efficient Neuromorphic Continual Learning with Local Learning Rule and Sub-Network Freezing Strategy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31927 - AU-Harness: An Open-Source Toolkit for Efficient and Unified Evaluation of AUdio-LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.08031 - Privacy Accounting for Empirical Denoisers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27710 - Operationalising Weaker Faithfulness: Recovery, Ambiguity and Computational Limits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31724 - Interaction-as-a-Judge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17895 - Cautious Conflict-Free Inverse Gradient Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31855 - Tampered ML: Evaluating LLM Judgment of Machine Learning Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32114 - MS-TTRL: Breaking the Frequency Conflict in Multiple-Solution Test-Time Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32234 - AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20625 - Efficient Omni-modal Large Language Model Inference via Per-Query Modality Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31768 - Knowledge Distillation across Item and Code Spaces for Parallel Generative Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32943 - FC-PINO: High Precision Physics-Informed Neural Operators via Fourier Continuation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2211.15960 - Principled Nonlinear Concept Erasure and Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32516 - Flownomaly: Single-Step Conditional-Mean Recovery for Few-Shot Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32964 - How Much Do You Trust A Dog? Quantifying Hint-Following in Reasoning Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32055 - Solving and Learning Navier-Stokes Dynamics with the Neural Basis Method Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32167 - BAARC: Uncertainty-Driven Adaptive Partial Spectral Measurement to Full Reconstruction for Material Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32505 - The Standard Deviation in VICReg Buys a Safety Margin Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32630 - Transient Amplification in Cascaded Gradient Methods: Exact Minimax Laws and Tracking without Resonance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04031 - SABLE: Scalable Affine Bayesian Latent-space Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31495 - Batched NN 4D-Var: a performant hybrid model framework for the Integrated Forecasting System Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32582 - Cognitively Constrained Partners for Zero-Shot Coordination in Real-Time Partitioned Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31726 - Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31846 - Autoregressive Multimodal Anomaly Detection with Large Language Models for Microservice Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31722 - CFBrainAug: Modularity-Induced Counterfactual Brain Network Augmentation for Interpretable fMRI-based Autism Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32184 - Approximating velocity fields with planted point attractors via Neural-ODE for classification purposes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23550 - Scaling Laws for Safety Probes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30678 - Towards Adversarially Robust Multigraph Neural Networks for Financial Crime Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31718 - DBCM: Dual-Branch Calibration Module for Test-Time Adaptation in Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32071 - RootDown: Deploying and Benchmarking Models for Beet-Root Detection on Edge Devices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32275 - Near-Optimal List Replicability from Littlestone Dimension Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32853 - Forecasting Associations, Not Interventions: A Preregistered Causal Audit of Covariate-Aware Time Series Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31869 - POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07775 - A Mixture-Gated Theory of Anisotropic Representation Dynamics in Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23242 - PRISM: Promoting Sampling Diversity of Large Language Models with Implicit Stochastic Modulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32101 - Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06840 - Quantum-Classical Link Prediction on Dark Web Hyperlink Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32510 - MoLS: SNR-Guided Module-Wise Learning-Rate Calibration for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05794 - Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23405 - Optimal Multiclass Online Regret with Arbitrary Label Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32339 - Random Jump Forests Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32498 - Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32046 - GeneSpeak-FP: Target and Compound Retrieval from Observed Cell-Level Perturbation Signatures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17671 - Searching with Sparse Histories: Cross-Task Architecture Search from Incomplete Search Logs and Zero-Cost Proxies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32179 - Trusting the Tool: Asymmetric Deference of LLM Vulnerability Auditors to Static-Analysis Evidence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32876 - Benchmarking Vision-Language Models on Synapse and Neuron Proofreading in Connectomics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36492 - Flow-ERD: Agent-type Aware Flow Matching With Entropy-Regularized Distillation for Diverse Traffic Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.06957 - Contextual Decision Making: Predictive or Generative Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32584 - Convergence of Large-Stepsize SGD for the Cross-entropy Loss via Stochastic Lyapunov Stability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30930 - FinVerse: Toward More Realistic Evaluation for Financial Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03259 - On the Identifiability of Hybrid Deep Generative Models: Meta-Learning as a Solution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32748 - End-to-End Differentiable Diffusion Conditioning for Physics-Informed Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31721 - ARENA: Active Region attENtion Aggregation for interpretable solar flare prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32758 - Neural networks become centroid classifiers when trained on heavily corrupted inputs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11319 - Attractor-Vascular Coupling Theory: Formal Grounding and Empirical Validation for AAMI-Standard Cuffless Blood Pressure Estimation from Smartphone Photoplethysmography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10871 - If at First You Don't Succeed, Backtrack: Lightweight Recovery for Frozen VLAs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32941 - VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.06502 - When Does Dynamics Randomization Test Context Inference? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32414 - DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32969 - TENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32337 - TreeWY: Speculative Verification for Gated DeltaNet Hybrids Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20961 - Federated Nonparametric Regression with Heterogeneous Clients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32178 - Dynamic Relational Priming Improves Transformer in Multivariate Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.12196 - Rethinking Multi-View Fusion for Urban Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31850 - GeoLEON-CLIP: Graph-Anchored Multimodal Contrastive Learning for Geographic Region Representation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32311 - Hybrid SEIR Temporal Fusion Transformer Framework with SHAP Analysis for Interpretable Pandemic Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31673 - Track finding and particle identification performance with particle physics foundation models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31180 - Learning Positive Linear Combinations of ReLUs in Fully Polynomial Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32940 - Interpreting Supervised Pairwise Graph Representations: Local Evidence, Confounding, and Provable Post-hoc Correction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32611 - A Tutorial on Physics Constrained Machine Learning for Hybrid Modeling, Optimization, and Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32914 - Joint user-item allocation for e-commerce marketing campaigns Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09623 - Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10625 - Beyond Heuristics and Commercial Navigation: An AI-Augmented Decision-Support for Ambulance Travel Time Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31968 - From Parameter Rebasin to Functional Transfer Across Heterogeneous Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32581 - Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10623 - SKG in Practice: OOD Generalization Cases Across FourDomains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32314 - Harmful Responses Are Jailbreak Templates: Transferring Autoregressive Jailbreaks to Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31331 - Sustainability of TSFM Deployment and Pretraining: From Carbon Footprint Analysis to Mitigation via Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32859 - Nested Sparsity for Scalable Pretraining and Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31818 - Do Halting Heads Really Save Compute in Looped Language Models? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32246 - Acquisition for Spherical-Linear Bayesian Optimization on the Cube Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32628 - Demo: Generative AI helps Radiotherapy Planning with User Preference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.08996 - On the Limits of Stochastic Push-Pull over Time-Varying Digraphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32422 - Mostly Reading: What Open-Book Scores Measure in Document-Level LoRA Adapters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31017 - SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30329 - A neural density functional for polymer electrolytes with exact structure and transferable Coulomb coupling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12132 - Clifford Kolmogorov-Arnold Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05977 - Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13707 - GS-MoE: Training-Free MoE Compression via Groupwise Subspace Sharing and Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32009 - Probing the limits of forward screening and inverse design of crystal materials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32678 - ConsMSA: Semantic Distribution Consistency Learning for Multimodal Sentiment Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31731 - When Does Self-Supervised Pretraining Help Tabular Models? A Study of Label Scarcity and Missing Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24381 - Curvature-Aware Clipping: Mitigating Bias in DPSGD via Approximate Second-Order Information Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32175 - $\Psi$-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32177 - When and How Does Muon Precondition? The Role of Structured Gradient Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31728 - Distributed Sparse Interventions in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07128 - Empirical concentration for chains with infinite memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32265 - On Orthogonal Recurrent Neural Networks Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.04012 - Anti-coherence Regularized Absolute Scaling for Out-of-Distribution Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32255 - Differentiating Through Dual Prices: End-to-End Policy Learning Under Capacity Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04669 - RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32971 - EVOLVE: Uncertainty-Aware Multivariate Time Series Anomaly Prediction with Adaptive Prototype Memories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32189 - Adaptive Frequency Threshold Byte Pair Encoding for Mixed Natural Language and Structured Symbolic Corpora Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32921 - Reinforcement Learning with Multi-Step Transition Predictions: A Bellman Theory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32887 - Implicit Neural Representations for Variational Problems on Graphons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32147 - Learning Structured Sparsity for Large Models: Bridging Model Compressibility and Efficient Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31897 - Correct but Unselectable: The Hidden Interface Tax in Multi-Candidate Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32235 - Feature-Space Smoothing: Certified Robustness of Deep Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16200 - Earth embeddings are decomposable records of the land surface Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32617 - RobustNCL: Robustifying Neuromorphic Continual Learning under Transient Faults with Lightweight Detect-and-Cure Strategy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31954 - Kolibri: A Sovereign European Model on the Pareto Frontier Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31945 - DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32305 - Verdict Instability of OOD Scores under Reference Resampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00691 - CyberHull: Deterministic Malicious URL Isolation via Convex Hull Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27675 - CuraLoc: Repository-Level Fault Localization via Planned Code Inspection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31809 - Strongly Adaptive Online Learning with Time-Varying Movement Costs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32740 - Efficient Zero-Shot Video Anomaly Detection via Signal-Aware Adaptive Fusion (SAAF) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32486 - Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32955 - Softly Symbolifying Kolmogorov-Arnold Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.07875 - Exact Global Minimax Risk near Nonidentification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32546 - Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18971 - Causal Representation Learning for Generalisable Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27043 - Multi-Task Learning for Metal Alloy Property Prediction: An Empirical Study of Negative Transfer and Mitigation Strategies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.22740 - Amortized Thompson Sampling and Efficient Information-Directed Sampling for Simulator-Based Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32514 - SWE-Shift: Evaluating Coding Agents in Evolving Workspaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32196 - Generalization properties of the token perceptron: the role of embedding and vocabulary Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32788 - Learning to Be Monitored: Causal Bounds and Intervention-Aware Post-Training Recipes for Chain-of-Thought Monitorability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31733 - Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.26114 - Acoustic and Lexical Signals for Native Language Identification of Language Learners Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32382 - BrainRotViT: Transformer-ResNet Hybrid for Explainable Modeling of Brain Aging from 3D sMRI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.15188 - Data Quality Audit and Bivariate Temperature-Humidity Analysis of a Long-Term LoRaWAN Network: Anomaly Detection, PCA, Clustering and Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32438 - Depth-Dependent Safety Geometry in Vision-Language Models: Layer-Wise Localization and Bidirectional Refusal Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32182 - DT-JEPA: Learning to Predict Future Representations for Decision-Making Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32657 - Approaching I/O-optimality for Approximate Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23751 - Aligning Large Language Models with Human Feedback: Mathematical Foundations and Algorithm Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31862 - Decode Late, Multiply Once: Rethinking the Dot Product for Quantized Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31913 - From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13221 - Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless $l^p$ Norm Solution for Fast Adversarial Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.02360 - Norm-optimal model order reduction in reproducing kernel Hilbert spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28224 - DualGSL: Prior-Guided Graph Structure Learning with Node-Adaptive Prediction Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32462 - Does LeWorldModel Preserve Local Action Geometry? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31716 - The Path to NDE 4.0: A Review of Algorithms, Techniques, and Strategies for Autonomous Inspection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31704 - Reuse, Rewrite, or Reject: Evidence-Constrained Trace Reuse for Repeated Mobile GUI Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31712 - A Model-Agnostic Correction Framework for Short-Term Building Load Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31959 - Collaborative In-Context Learning for Indoor Radio Map Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31702 - Speculative Diffusion is a Tale of Two Tradeoffs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31819 - On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32770 - Tabular Foundation Models for Credit Risk Prediction: A Dedicated Review and Empirical Comparison Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18147 - Not All Retained Clients Are Equal: Client Selection for Federated Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31786 - Bandits with Probing: Optimal Coverage and the Role of Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15248 - Do VLAs Know They Will Fail? Interpretable Success and Failure Patterns in Physical AI Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32208 - Residual-Based Adaptive Refinement in Hybrid Variational-Collocation PINNs for Singular Elliptic PDEs with Mixed Dirichlet-Neumann Boundary Conditions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26458 - Decoupling Patient Personas and Clinical Workflows: A Dual-Agent Approach to Realistic Medical Dialogue Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32443 - Agreement rather than normalisation keeps depth reusable in looped language models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31943 - Online Continual Learning in Edge-Cloud Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32472 - Early learning in large residual networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31783 - Democratizing LLM Training with the Edge: Challenges, Systems, and the Road Ahead Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32215 - Complementing DINO Features with Image Structure for Part Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32293 - PoKER: A Probability of Kill Estimation Rate Model for Air-to-Air Missiles Using Machine Learning on Stochastic Targets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32864 - Semantically Rich, Metrically Affect-Blind: A Geometric Blind Spot in Modern Text Embedders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32122 - Efficient Benchmarking Is Just Feature Selection and Multiple Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25773 - SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06513 - Conditional Flow Models for Offline Maximum Entropy Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32125 - REACT: Representational Early Analysis and Control of Chain-of-Thought Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.32113 - Not All Information Is Worth Asking For: Decision-Informed Information Seeking with LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32181 - Direction-Aware Token Credit Assignment with Reward-Model Gradients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32772 - Learning from Hypervectors: A Survey on Hyperdimensional Encoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2308.00685 - Train4Merge: RL or SFT---Which Yields Better Teachers for OPD-Based Model Merging? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32303 - Online Distributional Prediction via Latent Cluster Geometry Under Drift and Corruption Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18778 - How do standard time series forecasting benchmarks translate to finance? A broad study of risk adjusted performance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01820 - PaperScorer: How Predictable Is Paper Acceptance? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31791 - Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30474 - CARES: Coverage-Aware Replay Exemplar Selection for Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32799 - Prediction-Powered Data Fusion for Treatment Effect Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12332 - Decoupling candidate dual AGN from chance superpositions in the GOTHIC survey via a deep-learning framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24164 - Sharp Bounds on the Winner's Bias under Independent and Nonnegatively Correlated Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31948 - Sharpness-aware Orthogonalized Momentum Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32465 - StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08934 - Detection and Validation of Hidden Subgroup Disparities in Clinical AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32362 - Stochastic Inverse Problem: stability, regularization and Wasserstein gradient flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.00229 - Neural Disjunctive Normal Forms for Learning Exact Rank Filters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32203 - Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32059 - Input Bias Correction in Gaussian Process Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31920 - Convex Equilibrium Potentials for Monge--Amp\`ere: Curvature Bounds and A Posteriori Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31386 - On the Limits of Sparse Linear Model with Shuffled Differential Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32822 - From Dueling Bandits to Episodic MDPs: Learning with Adversarial Preference Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.11706 - CoPiT: A conditional Position-induced Transformer for aerodynamic field prediction on unstructured meshes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32299 - Cross-Scenario Controller Parameter Transformation from Real-World Driving Data through Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32719 - What Transfers from Training-Only Priors? Separating Knowledge, Ordinal Targets, and Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11146 - ReMedI: Inference-Time Refinement and Self-Distillation for Controllable Molecular Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32103 - Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16892 - Rethinking LoRA Initialization for Robust Asymmetric Learning Rates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32142 - How Should Transformers Encode Numeric Values in Electronic Health Records? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01391 - TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31995 - DeFAb: A Dataset for Grounded Scientific Discovery through Defeasible Abduction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18557 - Internal Discrepancy for Contrastive Learning: Generalization Bounds and Downstream Behaviors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32729 - Supervised Source Separation of Electric Vehicle Interior Noise Using a Hybrid Transformer Architecture Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32310 - DIGOM: Disentangled Interaction Graphs for Outcome prediction in Multimodal healthcare Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32451 - SyncPro: Synchronous Reasoning and Responding for Proactive Streaming Video Understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32132 - Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31670 - OpenAttention: One Percent Is Enough with Tail Proxies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30951 - Discretization and Statistical Consistency of Functional Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04531 - Let's Do Turbulence Right: In Space and Time! Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32601 - Mitigating the Likelihood Paradox in Flow-based OOD Detection: An Entropic Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09581 - Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31884 - Autoregressive Physics-Informed Neural Operator Surrogates and Joint 4-D Seismic-Production Bayesian History Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31677 - Rewriting Scaling Laws for Synthetic Data with Compute and Data Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31867 - Differentially Private Synthetic Data via Generalized Moment Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30196 - Half-Truths Break Similarity-Based Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23906 - Efficient Exploration for Iterative Nash Preference Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01382 - Neural LoFi with Backward Coupling: A Spectral Theory of Cross-Layer Feature Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32849 - Clean-label Poisoning Attack and Defense Game for Federated Learning in Vehicular Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32765 - Benchmarks Are Surprisingly Compaction-Friendly Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31778 - A Dynamic Inventory Rationing Model for Last-Mile Delivery of Medication in Liberia's Community Health Program Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32051 - Why Does Counterintuitive Likelihood Behavior Rarely Emerge in Tabular Anomaly Detection? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09593 - Multi modal perceived conversation success prediction for spontaneous autistic and non-autistic dyadic interactions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31682 - Multiplicative vs. Additive State Coupling in Learned Optimizer Schedules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32801 - Combinatorial Characterizations of the Learnability of Conditional Distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31890 - Dementia-R1: Reinforced Pretraining and Reasoning from Unstructured Clinical Notes for Real-World Dementia Prognosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.03018 - Accordion: Elastic-Depth Inference via Fixed-Prefix Layer Looping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32492 - Beyond Data Schedule: Fast LLM Pretraining on Data Mixtures by Loss-Reweighting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32141 - Foundations of the Scaling Law Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27789 - DRIVE: Fine-tuning via Data Contribution- and Diversity-aware Weighting with Prior Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32501 - Chimaera: A Mixture-of-Graph-Experts Architecture for Cross-Task and Cross-Dataset Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08709 - MPQ: A Message-Passing View of Post-Training Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32127 - Topological Equivalence of Spectral and Density Cluster Hierarchies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31909 - EvoSkill v2: Fully Agentic Skill Evolution from Benchmark Adaptation to a Stateful Evolver Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25931 - Singular Geometry of Low-Rank Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32854 - PASTA: Prompt-Aware Annealed Diffusion Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32390 - Momentum in large-batch training: Polyak enlarges the critical batch size, Nesterov improves data efficiency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02728 - U-STS-LLM: A Unified Spatio-Temporal Steered Large Language Model for Traffic Prediction and Imputation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11735 - Strictly Replicable Realizable Learning: Unknown Marginals, Finite-Class Interpolation, and the Cost of Shared Randomness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26944 - When Human Corrections Travel: Safety in Federated VLA Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32888 - Scaling Transformer Energy-based Models For High Quality Image Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31889 - U-NeXt: General-purpose event detection for neonatal EEG Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32811 - Head Dimension Matters in Language Models for Long-Context Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.32213 - Maximum Likelihood on the Joint (Data, Condition) Distribution for Solving Ill-Posed Problems with Conditional Flow Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2208.11782 - Analysing Austrian Parliamentary Speeches by Predicting Party Affiliations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32515 - Interpretable sparse fine-tuning with TopKLoRA enables faithful circuit discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32866 - Beyond Local Accuracy: Benchmarking the Rollout Reliability of PDE Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31935 - Rethinking Representation Geometry in Supervised Contrastive Learning under Long-Tailed Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32039 - NUViT: Vision Transformers for Fourier Space Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32041 - Constitution-Guided Watermarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09552 - Regret-Based $(\epsilon,\delta)$-optimal Stopping Criteria for Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22561 - KnitTrans: Coordinated Trajectory Transfer for Effective and Efficient LLM Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32389 - Iterative Policy Optimization: Batch-Online Multi-Turn RL via Single-Turn RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.21638 - Learning Bidirectional Causal Interactions with Heteroscedastic Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22313 - Shared Is Not Enough: Predictor Width and Factor Readability Under Masked Latent Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32562 - MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13297 - Controlled Evaluation of EEG Foundation Models: Random Initialisation, Band-Power and Validation-Selected Probes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32067 - Under the Influence: Evaluating and Improving LLM Vigilance in Agentic Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.21262 - Sparse Bayesian Neural Networks via Sticky Piecewise Deterministic Markov Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32753 - Recommender regret for improving regularised RL estimation with bandits and MCTS Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32910 - Training-Free Task Vectors for LLM Behavioral Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09054 - WL-SeqVAE: Sequence-Based Graph Generation Using Variational Autoencoders and Weisfeiler-Leman Colors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32650 - REDAR: Reinforcement-Driven Adaptive Regularisation for Class Incremental Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31991 - Do Language Models Trust Their Own Justifications? A Study on Functional Consistency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32665 - PathJev: Decision-Native Vision-Language Modelling for Histopathology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32478 - $\tilde{O}(\sqrt{T})$ Regret and Polylogarithmic Constraint Violation for COCO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03983 - Trajectory Matching: Discrete Flow Matching with Structured Actions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32602 - MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09983 - Learning to Predict, Discover, and Reason in High-Cardinality Event Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16313 - When to Trust Memory: Retrieval-Guided Probabilistic Spatiotemporal Forecasting under Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32329 - Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.33503 - How Much Fresh Data Should CTR Recalibration Use? A Temporal Evaluation of Post-hoc Calibration Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.33168 - Theoretically Sound Item Similarity Measures for Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34402 - DyHist: Query-Aware Historical Dynamics Modeling for Temporal Knowledge Graph Extrapolation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.33473 - When Fusion Order Matters: Insights on Progressive Multimodal Representation Learning for Cross-modal Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35125 - HARP-LoRA: Hierarchy-Conditioned Rank Projection for Low-Rank Adaptation in Scientific Table Understanding Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34589 - LoopGR: Parameter-Efficient Scaling for Generative Recommendation via Recurrent Depth Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34157 - Learning to Remember: Advances in Memory Mechanisms for Large Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35089 - Beyond "[at]": A Large-Scale Measurement of Email Address Presentation on Computer Science Scholars' Homepages Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35499 - Towards a Unified Framework of Optimal Input-Side Dimensional Configuration for Deep CTR Prediction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35695 - Lessons from Luck: Do LLM-Written Lessons Carry Chance into an Agent's Next Decision? Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.33029 - Factual Yet One-Sided: Stance Poisoning and Evidence Balancing in Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34294 - The Geometry of Agent Memory: Forecasting Retrieval-Bound Memory Failures, and Characterizing Its Limits Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.26433 - Good Scores, Bad Data: A Metric for Multimodal Coherence Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2603.25924 - Discovering Topics from Linear Autoencoders Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34739 - Agreement Between Reconstructed and Native GDELT GKG Records: A Field-Level Baseline Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35358 - $\Delta\tau$-Bench: Pushing Agents Toward a Moving Capability Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34238 - Bridging Search Intent and Tabular Data in Dataset Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.33936 - PinGER: Token-Efficient Generative Retrieval with Semantic IDs Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.33435 - Hypergraph-Enhanced Evidence Selection for Long-Context Multimodal Document QA Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35542 - TriageRAG: Failure-Aware Self-Training for Adapting Retrieval-Augmented Language Models to Specialized Domains Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.33776 - SearchJev: A Calibrated System-1 Model for Search Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.05107 - Do Similarity Measures Measure Similarity? How User Activity Creates Phantom Correlation in Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35765 - RefinedGAW: A Refined German Academic Web Dataset Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34572 - UniRec: Cross-stage Multi-Task Fusion with Preference Optimization for Cascaded Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.11052 - FormBench: A Benchmark for Fine-Grained Retrieval in Formulation Patents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30175 - SLIDE: Search-to-List Item Distillation for Single-Rollout Generative Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34764 - 5W1H+Which: Context-Valid Semantic Indexing with Progressive Ontology Binding Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.35184 - CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.07458 - DPE-Rec: Diversity-Preserving and Efficient Diffusion Language Model Recommendation for Bundle Construction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34700 - Read the Route: Attention-Steered Hypergraph Retrieval for Multi-hop RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35412 - Navigating Ideation Space: Decomposed Conceptual Representations for Positioning Scientific Ideas Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2601.08901 - Cross-Domain Sequential Recommendation with Representation-Level User Transfer Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35550 - Agent Memory as Recommendation: Recommender-System Design for Long-Term Memory of LLM Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34673 - An Interpretable CF-RL-TOPSIS Fusion Model for Skills-Aware Talent Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.24155 - Reading the Registers of Honorius III without Manual Line Transcription: Forced-Aligned HTR, End to End, Modular or Hybrid Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35085 - SkillQR: Agentic Skill Discovery for Reason-Intensive Query Rewriting Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.33768 - Tiny Suffix Arrays Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35543 - Beyond Behavioral Accuracy: Evaluating Individual-Level Fidelity in LLM Investor Simulation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.26524 - Holo-NN: Holographic Nearest Neighbor Search via Compressive Sensing Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.33224 - Improving the Performance of Compressed Transformers with Post-Hoc Embedding Alignment Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2602.14635 - CRIM: Composable and Reusable Item Memory for Efficient Personalized Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35323 - ACARE: Agent-Context-Aware Reranker for Iterative Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35840 - Useful Diversity or Hallucinated Variety? Persona-Conditioned Synthetic Query Generation for E-Commerce Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35102 - Knowing When the Evidence Is Enough: Requirement-Directed Search with Horn-Closure Certificates Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34684 - ECHO: Efficient Cascade with Homogeneous Operators for Distillation-Guided 100K-Sequence Modeling Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.28569 - The Price of Scale in Proactive Memory Recall Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34507 - Recovering Business Rules as Cascade Lookups for Enterprise Field Prediction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34258 - The Delayed Countdown Method for Validating Review-Oriented AI Workflows in eDiscovery Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.31311 - MIDA: Multi-Interest Decoding with Adaptive Aggregation for Session-based Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34192 - Decision-Native Recommendation with Large Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34124 - CA-HNM: Constraint-Aware Hard Negative Mining for Dense Retrieval with Structured Domain Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35045 - Reinforcement Learning for Controller Parameters in the Auto-Bidding System at Pinterest Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.33248 - Comparing GenAI to Machine Learning and Manual Review for eDiscovery Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.16925 - AllSERP: Exhaustive Per-Element Enrichment of the Versatile AdSERP Dataset Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.04949 - Geometric Gain Graph: Zero-Token Graph Construction for Multi-Hop RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19622 - Unified Heterogeneous Feature Interaction via Effective-Rank Scaling for Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35318 - A Domain-Aware Pipeline for Structured Extraction and Retrieval-Augmented Question Answering over arXiv Superconductivity Literature Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34391 - Finding Change in Satellite Archives from Text: How to Combine Before-and-After Images Efficiently Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.28571 - Scriptorium: System Design and Implementation of a Multi-Human, Multi-AI Collaborative Digital Library Search Platform Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.28929 - Separating Thinking from Spelling for Efficient Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.32980 - Cross-Lingual Information Retrieval in Tetun for Ad-Hoc Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34362 - Multimodal Requirements Traceability Link Recovery in Industrial Settings Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.34503 - Hallucination-Aware Multi-Agent RAG via Internal Attention Rewards Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35056 - Diagnosing and Mitigating Context Rot in Long-horizon Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.29718 - Reading Beyond OCR Noise: Robust Cross-Lingual RAG for Legislative Archives Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35240 - Octen-WebGR: Scaling Generative Retrieval to 200 Million Web Pages Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35256 - S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35518 - Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33024 - 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 - T2D: Target-to-Draft Model Pruning & Adaptation for Efficient Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34103 - STEP: Soft Trajectory Estimation of Prediction Correctness via Per-Step Probability Scoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34537 - Does the Outfit Change the Price? Context Halo in Vision-Language Model Valuation of an Identical Low-Cost Necklace Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34591 - Genotypic Triggers: Exposing Pharmacogenomic Blind Spots via Host-Specific Backdoors in Generative Antimicrobial Peptide Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06779 - Adaptive Retrieval, Selective Answers: Evaluating Conformal Factuality in Agentic RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34872 - Prompt PerturbAItions: Mechanisms of LLM Response Inconsistencies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30913 - BehaviorMem: Building and Evaluating User Memory from Real-World E-Commerce Behavior Streams Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34790 - SAMPA: Transformer-based segmentation of prosodic boundaries in Brazilian Portuguese Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07408 - Dynamic Short Convolutions Improve Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03825 - What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05533 - The Patient Is Always Right? Evaluating Sycophancy in Medical Diagnosis with Graded Patient Beliefs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34013 - DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00996 - Reasoning or Just Prompting? Probing the Mechanism of Latent Chemical Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34173 - Atomic Security Concerns: Towards a Foundational Language for Security Knowledge Representation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35782 - Strong yet Controllable LLM Abstention without Learning to Abstain Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16318 - Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33180 - Style over Substance? Linguistic Bias in LLM-based Peer Review Copy title Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35254 - Entropic Control for Homeostatic Optimization: Pre-empting Catastrophic Forgetting via Dynamic Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34182 - Grounding on Request: Learning Modality Control in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33841 - Rhythm of the Deep: Two-tier acoustic organization of sperm-whale codas from click waveforms to coda sequences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16084 - A Benchmark for Controllable Speaking-Style Captioning in Audio-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33036 - When Does Better Acceptance Pay? A Controlled Study of Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24993 - Heard Enough to Act: Early Tool Calling in Spoken Dialogue Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34653 - When the Persona Contradicts the Line: Diagnosing Plan-to-Synthesis Failures in Chain-of-Thought TTS Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35008 - CoLink: Global Compression and Knowledge Linking for Multi-Turn Dialogue Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34335 - FATE-5: Faithful Alignment of Trait Expression for Continuous Big Five Personality Control Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34889 - Quantifying Meaning with SCAPE-T: Semantic Complexity from Encoder-Only Transformer Attention Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33441 - LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06795 - Not One Belief: Answer Payloads, Persistence, and Dissociated Confidence Signals in Conversational Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.35694 - A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16548 - KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.21856 - "High-Quality" Data for Early-Stage Instruction Tuning: An Empirical Study of Data Quality Metrics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33969 - Hierarchical Skill Evolution for Coding Agent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35616 - MiRL: Error-Targeted Reinforcement Learning for Correcting Terminal Agent Misbehaviors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35697 - Examining form-based linguistic productivity in people and large language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33433 - Efficient Proof Generation for Lean Statements with Multiple Candidate Answers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34490 - CoSA: The Conflict of Skills Attack in Real-World LLM Agent Ecosystems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35082 - Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07600 - Jointly Modeling Preferences and Imperfect Decision-Making in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33651 - RAGing Against Misogyny: Improving Implicit Misogyny Explanations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35094 - Is this Citation on Point? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12571 - Improving the Chain-of-Thought Compressibility of Pruned Reasoning Models via Long--Short Contrastive Pruning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34336 - Learning Faithful Reasoning Processes with Spatio-Temporal Latent Dynamics for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26893 - One Scan is Enough: Demonstration-Free Adaptation for Language-Guided Navigation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33794 - RIVO: Lightweight Adaptive Rerouting for Deep Research Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15910 - Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21073 - The Lexical Imprint of Pre-training Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10657 - Prefix Sharing Is a Sorting Problem Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.13692 - Trainable Boundary-Keeping Where No Formal Answer Exists: A Controlled Knock-In Study of Reward Training in Evidence-Sufficiency Judgment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35226 - CulturalRiddles: A Multicultural Benchmark of Riddles Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29968 - Natural Jammers: When Non-Robust Features Become Antagonistic Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34785 - Veil-Then-Reveal: Protecting PII Privacy via Reversible Pseudo-Anonymization in Zero-Trust User--LLM Interaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22800 - Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25866 - Whether or Where? Tail Calibration Signals Finite-Budget Reward Hacking in Best-of-N Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34375 - FlexA-Mem: Budget-Adaptive Agentic Memory for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33274 - The Social World Model Evaluation Gap Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33014 - DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35201 - MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21091 - Beyond Prompts: A Systematic Study of LLM-Based Machine Translation Evaluators Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33741 - The Geometry of Emotion Representations Across Scale, Depth, and Instruction Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35411 - Auto-AdvER: Disentangling Condition, History, and Commercial Offers in Automotive Advertisements Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.05655 - Understanding Jev-Style System One Models: Does Structure Reduce Selection Bias? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35826 - ImgMT: Wikipedia-based Dataset For Evaluating Text-in-Image Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35416 - Web Agents Should Adopt the Compile-and-Execute Paradigm Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2605.14290 - Memory Tax: Dissecting the Net Value of Agent Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34073 - Amplitude-Only FFN Intervention for Tool-Structured LLM Inference: Method, Gated Evaluation Protocol, and Cross-Model Empirical Results Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11183 - Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33956 - Improving Reasoning with Rollout Agreement for Group-Based Policy Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34951 - Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.23166 - Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33568 - A Reverse-Gold Theorem: Positive-Data Identification by Substrate-Bounded Contrastive Learners Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28747 - Semantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.18835 - Entity Matching using Decision Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34626 - Refined Assessment for Translation Evaluation: Rethinking Machine Translation Evaluation in the Era of Human-Level Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33749 - A False Average: Pooled CoT-Monitor Accuracy Conceals a Reasoning-Dependent Fragility Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00583 - LLMs are not stochastic parrots: Evidence for meaning-mediated abstraction from conlang-like tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34187 - Transformer to GPT-5: Advancements, Limitations, and Future Directions in Large Language Model Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34281 - Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04971 - iPrefBench: A User-Centric Benchmark for Personalized Mobile Use Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34735 - FinLifeBench: Exhaustive Life-Event History and Financial-State Reconstruction from Longitudinal Banking Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01198 - Improving JEV Entailment Reranking with Span Readouts and Selective Adaptation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35654 - What Outcome RL Buys: Finishing, Reliability, Rarely Reach Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34894 - CausalMix: Data Mixture as Causal Inference for Language Model Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01104 - Where Models Converge and Humans Diverge: A Coverage Framework for Distributional Pluralism in Open-Ended Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05576 - The LLENS Platform for On-Premises Large Language Model Agents in a Japanese University Hospital: Development and Evaluation Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32151 - Adapt or Calibrate? How Local Labels Buy Certified Coverage in Medical VQA Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15910 - Position Matters More Than Channel: Talking a Language Model Out of a Correct Answer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34809 - Wave Is All You Need: A Quantum Language Model Based on Fully Connected Quantum Boltzmann Machine Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34492 - SLICE-Mem: Salience-Gated Lightweight Information Curation for Efficient LLM Agent Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33015 - RoleHear: Pseudo-Labeling for Semi-Supervised Role-Attributed Streaming Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33765 - Toward Global Large Language Models in Medicine Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.02186 - ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34886 - Quality over Quantity: Rethinking Data and Model Assumptions for Bengali Coreference Resolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35114 - Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08362 - BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.22678 - How Do Small Coding Agents Use Code Graphs and Embeddings? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33958 - Task Format as a Factor in Adaptation: A Controlled Comparison of LoRA and Full Fine-Tuning for Prompt-Safety Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33813 - Learning When to Commit: Schedule Distillation for Fast Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35804 - Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.15194 - Can JEV Support Clinical Trial Criteria Assessment? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35721 - Adaptive Transfer of Representational Signatures for LLM Reliability Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33442 - VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30090 - What the Abstention Option Measures: Refusal Loss, Sampling Churn, and Option Capture in Distilled Small Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28639 - An Algorithmic Account of Few-Shot Concept Induction in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35533 - VerifyMAS: Hypothesis Verification for Failure Attribution in LLM-based Multi-Agent Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17467 - Whispering Wisely: Smart Subset Selection for ASR Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32997 - SVD-Attention: Efficiently Analyzing Attention Blocks in Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34971 - LoWAgent: A Low-Resource Multilingual Benchmark for Web Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27205 - DynEdit: Dynamic Entropy-Guided Sequential Editing for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34768 - Reversible Pseudonymisation of Documents Sent to External LLMs: an Open Bilingual Benchmark and an Engine Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34012 - Linear-Time Context Compression with State-Space Encoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33006 - Birth, Death and Diff: Insertion-Based Sequence Generation with Corrections Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34310 - Speculative Forking: Turning Idle Wait into Parallel Exploration for Repository Environment Setup Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33129 - MIS-VQA: An Annotation-Driven Surgical Vision-Language Dataset for Complex Surgical Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34210 - Distill, Debate, Discover: Grounding Multi-Agent Research Ideation in Graph-Distilled Insights Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33366 - Truncated Reasoning Under a Budget: Evaluating System-1 Models as Decision-Makers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25768 - Trace Integrity for LLM Data Agents: Auditing Structured-Data Computation Beyond Answer Accuracy in Real-World Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26036 - "I Strongly Suspect This Website Is a Scam": Benchmarking PII Leakage and Detection without Defense in Autonomous Web Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00497 - Making Reasoning Visible: Configuration-Aware Diagnostic Modeling for Adaptive Scaffolding in Structured Reasoning Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35609 - MANTIS: Multi-Axis News Transformations for Instance-Wise Stress Testing and Worst-Case Training in Fake News Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35475 - Hierarchical Alignment: Block-Level LoRA-DPO for Preference Tuning in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.12044 - Harness Scaling for Generalizable Agentic Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29458 - Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17668 - Explore More, Validate Less: Efficient Reflective Prompt Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27367 - CANDOR: Chance-Calibrated Neighborhood Discordance in Frozen Encoders for Medical Imaging Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18451 - Role-aware Heuristic Episodic Attention for Conversational LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.06869 - PathKGen: Pathology Knowledge Assisted MLLM for Explainable Histopathology Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33691 - DocTalk: Enhancing Medical Knowledge Retrieval via Fine-tuned Large Language Models with Chain-of-Thought Reasoning for Robust Clinical Decision Support Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34871 - The LALA Benchmark: Evaluating Literary and Linguistic Analysis in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34080 - Parametric Session States Recover Retrieval Intent without Replaying History Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33047 - Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34149 - When Agents Collude: Weak-to-Strong On-Policy Distillation for Mitigating Strategic Deception in Multi-Agent Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33011 - Position, Role or Label? A Controlled Study of Instruction Conflicts in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33201 - Skill$^{\infty}$: Recursive Self-Improvement for Agent Skill Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35434 - Towards Root Memory: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23283 - HerHealthGPT: An Evidence-Grounded Conversational AI System for Women's Reproductive Health Copy title Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33931 - Can LLMs Trust Appropriately? Evaluating Calibrated Reliance on Imperfect Partners Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34107 - Ranking Is Not Deciding: Benchmark Shortcuts and Operating-Point Collapse in Query-Time RAG Poisoning Defenses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33849 - SUDO: From Scientific Publications to Global Scholarly Discourse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33018 - Training in translation tools and technologies: Findings of the EMT survey 2023 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.22735 - Circuit Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25002 - Higher Reasoning Effort Improves Reference Verifiability and Changes Reasoning Summaries in GPT-5.5 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34212 - Integrate the Reward, Don't Sample It: Window Likelihood for Interruptions and Backchannels in Full-Duplex Speech Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35581 - RSI Arena: Towards Recursive Self-Improvement with Human Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33624 - Rethinking Retrieval in the Long-Context Era: Training-Free Semantic Trees for Adaptive Context Construction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34146 - Toward Neuroadaptive Communication Interfaces: A Framework for Personalized Speech and Language Support Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34457 - Quantitative Generalization Bounds for Multi-Layer Transformers: A Few Long Strings can Beat Many Short Ones Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35715 - StateLoop: Persistent State for Looped Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35544 - Probing the phon* representations of the Mimi codebooks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35432 - Knowledge-Guided LLM for Intent-Driven Service Orchestration in Integrated Terrestrial and Non-Terrestrial 6G Networks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33007 - High Scores, Hidden Failures: Evaluating Codebook-Based LLM Content Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35179 - Prospect Theory in Large Language Models: A Meta-Analysis of Loss Aversion, Diminishing Sensitivity, and Probability Weighting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33103 - DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21561 - MechAlign: Evaluating Semantic Alignment at the Project Level in Mathematical Formalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35269 - Entity-Aware Evaluation of OCR Systems for Historical Document Transcription Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33004 - Large Language Model probabilities cannot reliably distinguish between possible and impossible language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.15114 - Synthetic linguistic data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34215 - GraphDancer: Training LLMs to Explore and Reason over Graphs via Curriculum Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02518 - One Model, Two Paths: Balancing Single-Pass and Looped Performance in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33517 - Continuous Diffusion Scales Competitively with Discrete Diffusion for Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18530 - Schema-Free Text-to-SQL: Learning Enterprise Database Structure from Query Logs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33946 - HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25421 - INVAR-Agri: Detecting Discrepancies in Multilingual Operator Manuals of Agricultural Implements with a Fine-Tuned LLM Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35423 - Center-of-Mass Interpretation of Evolution Strategies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35865 - Where and What to Reward? Understanding Generalization Between Verifiable and Open-Ended Domains in Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15464 - Beyond the Opening: Tracing the First Token's Persistent Influence on Reasoning Length Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34350 - What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34491 - Do Latent Tokens Think? A Causal and Adversarial Analysis of Chain-of-Continuous-Thought Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.21711 - What Makes a Question Curious? Measuring Model Curiosity in Human-LLM Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33950 - Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29109 - Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.15552 - Open-Jev Judgments on CallScreenBench: Calibrated One-Pass Scam Screening with a Small Language Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23959 - Semantic Atoms for Scalable Text Analysis in Data Analytics in the Era of LLM-Based Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34860 - Automotive-ENV: Benchmarking Multimodal Models in Automotive Cockpit Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.21143 - Implicit Beliefs as Scalable Process Rewards for Strategic Persuasion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33527 - NumTrace: Auditing the Number Provenance of Financial Analyst Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34887 - TIAgent: From Natural Language to Grounded Agentic Workflows for Computational Pathology Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32993 - EdgeDeID: A 0.6B Clinical De-identifier Trained Without Real Patient Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33839 - LTEM: LLM-Friendly Table-Enhanced Markdown for Table Understanding and Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29188 - Why Does Structured Output Fail? An Empirical Study of Prompt-Enforced Pydantic Schemas Across Nine LLMs Source: arxiv-cs-cl Topic: AI Research (+AI, FastAPI, Python) URL: https://arxiv.org/abs/2610.33949 - JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31142 - Quality-Controlled Reply and Summary Data for Post-Training Small Language Models in AI Call-Screening Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25458 - Linear Probes Transfer from Base to Distilled Language Models despite Rotation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35586 - Improving VLMs on Scientific Chart Analysis via Autonomous Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35077 - Gender Associations in LLM-Mediated ADHD Self-Diagnosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33697 - Xing USP: A Cross-Family Semantic Contract for Information Extraction and Intent-Slot Parsing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34343 - A Multimodal Framework for Measuring Creator Communication on Short-Form Video Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33043 - Large Language Models: A Plain-Language Overview for Engineers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34585 - Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35685 - SignVerse-2M: A Two-Million-Clip Pose-Native Universe of 55+ Sign Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01720 - PriFT: Guiding Supervised Fine-Tuning with Pretrained Priors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09396 - QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24218 - Credit Without Ground Truth: Claim-Matched Evaluation of Step-Level Credit with Finite Executed Replay Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19760 - Expert L2 English Speech Evaluation on a Gaming PC: Accuracy, Fluency, and Prosody with XLS-R, XEUS, and PhoneticXeus Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26406 - GPDPO: Learning from Reward Conflicts via Group Pareto-Dominance Policy Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35480 - Beyond Words Alone: Disentangling Distributed Evidence for Visually Grounded Cultural Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35482 - Loop the Loopies! Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.16051 - Learning What to Ask for Tomorrow: Active Preference Acquisition for Long-Term Personalized Web Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31107 - Question-Specific Knowledge Graphs for Efficient Visual Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35942 - SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35743 - LoopFold: Parallelizing Recurrent Depth in Looped Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35556 - Task Success Is Not Enough: Side-effect-Aware Evaluation of Tool-Using Language Model Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34167 - Merge-Based Vocabulary Extension Stalls at the Pre-Tokenizer: An English-Preserving Repair for Nepali, Tested in Continued Pretraining Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33016 - Naturalistic measure of social norms alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23420 - Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17558 - Propasafe-Hybrid: A Text-Based Hybrid Propaganda Detection Tool Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33464 - Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.14373 - The Straight and Narrow: Do LLMs Possess an Internal Moral Path? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10307 - Lost in Translation: Investigating Systematic Discrepancies between Parallel English and Chinese Names of American Chinese Restaurants Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35191 - Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12689 - AdaptTok-Indic: Script-Aware Adaptive Tokenization for Indic Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33017 - Does the Voynich Manuscript Mean Anything? Calibrated Tests Find Little Trace of Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34499 - LADDER: Diagnosing Domain-Level Self-Assessment Under Noisy Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34737 - Preference Optimization Improves Definition Generation: Semantic Change in EU Institutional Sustainable Finance Disclosures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33357 - Gefen: Optimized Stochastic Optimizer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13894 - From Self-Confidence to Statistical Accuracy: Scaling Human-in-the-Loop Evaluation with Direct and LLM-Assisted Auditing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35698 - Priority-Preserving Advantage Aggregation for Multi-Reward Policy Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34862 - Quantifying Claim Smoothing by LLM Research Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35793 - SATFormer: Learning When to Use Early Value Residuals in Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03953 - Two Uncertainties Are Not One: Disagreement versus Decision-Risk in Cheap Structured Content Moderation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33258 - From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12836 - SimPOTrans: Self-Adaptation for Offline-to-Simultaneous Speech Translation via Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35042 - Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35295 - The Emergence and Sparsification of a Syntactic Circuit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33299 - Agents' Last Exam Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05405 - IntentDelta: A Human-Constructed Benchmark for Evolving User Intent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33806 - Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35671 - One Mean Log-Mel Vector per Phoneme: Simple and Fast Text Injection for Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34623 - Conceptizer: Next-Token Prediction Is Not All You Need Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33027 - RubriX: A Fast, Fine-Tunable Non-Autoregressive Rubric Judge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34875 - Budgeted Prompt-Set Expansion and Refinement for Language Models via Simulation Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.08164 - ActTail: Global Activation Sparsity in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12272 - Leadership as Coordination Control: Behavioral Signatures and the Recovery-Advantage Boundary in Multi-Agent LLM Teams Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19111 - Words Are the Voice of the Mind: Depression Severity Estimation from Social Traces via Mental-Guided Evidence Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33586 - Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24965 - Embedding-Based Educational Taxonomies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33694 - P2N: Reusing Deep Representations for Greater Effective Depth Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25076 - Stylistic Evolution and LLM Neutrality in Singlish Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06580 - Preserve to Expand: Source-Aware Adaptation and Model Merging for Multilingual LLM-Based ASR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35846 - Anatomy of a Scam Call: What 10,000 real scam and spam calls reveal about how phone scammers operate Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24127 - Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.28075 - Reason or Recite: Complementary Specialists with an LLM Judge for Traffic Anomaly Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34993 - Incremental Predictive Value of LLM Tutoring Interactions for Student Performance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33488 - A Corpus of Real Scam- and Spam-Call Conversations from an Active Voice-Agent Honeypot Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29528 - Where Prefill Expert Reduction Hurts MoE Models: A Few Prompt Tokens Carry Most of the Short-Answer F1 Loss Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22454 - A Russian, a Brazilian, and a German Walk into a Bar, Ask the Same Question-- And Get Three Different Answers: Profiling LLM Perspective Diversity on Contested Topics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34278 - MTA-Zero: Self-Improving Multimodal Deep Search via Online QA-Solver Co-training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33799 - From Questions to Queries to Insights: A Schema-Grounded Agentic Workflow for Natural-Language Crash Data Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35054 - DecisionTraceBench: Tracking Decision-Critical Information in Multi-Party Spoken Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34746 - Do Language Models Understand Igbo Culture? Beyond Multiple Choice Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35168 - Investigating and Alleviating Harm Amplification in LLM Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02423 - SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24259 - AndroidFlux: Evaluating and Reward Modeling Failure Recovery Capabilities in Mobile Use Multimodal Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34384 - Five Architectures, One Shared Space Cross-Model Representational Alignment Without Weight Merging Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33495 - Multi-Agent Retrieval-Augmented Causality Assessment (MARCA) of Individual Case Safety Reports in Pharmacovigilance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33279 - Synthetic Child-Adult Interactions Are Not Developmentally Plausible Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35029 - Intervention-Certified Amplification: A Validity Gate for $\sigma$-Weighted Post-Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33882 - Identically Trained Language Models Break on Different Jailbreaks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34074 - SEDATE: Do Large Language Models Share an Aggression Circuit Across Languages? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33542 - OpenESM: Energy-Steered Models Are Scalable Foundation Learners Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33005 - Detecting Differences Is Not Understanding Structure: Large Language Models Fail at Graph Isomorphism Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09484 - Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.22458 - Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34137 - Late Attention Layers Alone Can Copy Entity Tokens, but Not Without Attending to Their Context Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35663 - Unified Context Evolution for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02304 - Each Insufficient in Its Own Way: Calibrating Language Models Across Varying Evidence States Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33237 - Human-LLM Alignment in Language Attitudes Toward Non-Native Japanese Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01629 - StateWise: Teaching Language Models to Track and Obey Evolving Constraints in Multi-Turn Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33766 - PreView: Enhancing GUI Grounding with Preprocessed Views and Cues Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33645 - From Belief Inference to Task Action: A Multi-Level Evaluation of Theory of Mind on Verifiable Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34759 - Mine or Yours? Mind-Bridged Language Models Take Each Other's Memories as Their Own Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33020 - TraceQuery: learning what to recompute from full-denoising trajectory in diffusion language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33008 - Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35328 - Can Multi-modal (reasoning) LLMs detect document manipulation? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.11021 - When Personas Become Harmful: Guiding LLMs with Global Citizenship Values Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33899 - How Does Post-Training Shape LLM Value Preferences? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33371 - Correlation-Aware Exploration for Long-Trace Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34949 - Robust and Fine-Grained Detection of AI Generated Texts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.11952 - Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28591 - Small Edits, Shifting Decisions: Benchmarking LLM Accuracy and Reliability on French Input Variants Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33493 - Counterfactual Test-Time Augmentation for Shortcut Removal in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33904 - UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33013 - Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33512 - Offline Language-Based Support System for Tactical Decision-Making in Air Combat Operations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35635 - Beyond Belief: Evaluating and Mitigating LLM Susceptibility to Misinformation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33962 - Of Chains and Gains: What Reinforcement Learning changes on Reasoning-based Image Quality Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33203 - Towards a Learnable Retriever for Textual Graph Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33511 - When Does GEPA Merge Help? A Mechanism-Level Diagnostic Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34027 - LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06285 - EXCISE: Locating and Excising Distracting Sentences in Medical Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35558 - LinearARD: Linear-Memory Attention Distillation for RoPE Restoration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.00004 - Ask Before You Answer: A Question-Driven Evidence Reasoning Architecture (QERA) for In-Context Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35083 - Rethinking Scientific Discovery in the Agentic Era Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03863 - From Writing Advice to Manuscript Governance: A Constrained-Transformation Framework for Academic Revision Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33001 - 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 - EviGround-CT: Sentence-to-Volume Grounding for Verifying LLM-Generated Chest CT Reports Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33038 - AskGLP1: A Knowledge Graph LLM Agent for Exploring GLP-1 Experience from Online Patient Narratives Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34987 - The Value of Memory in Language Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31303 - Can Language Models Learn While They Think? Testing Gradient Adaptation Across Architectures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33025 - The Hitchhiker's Guide to System 1 Models: Fast Decision-Making Beyond LLMS Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33775 - A Model-Theoretic Formalization of AlKhwaremis ilm alfaraid Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33629 - SkillShift-Bench: Benchmarking Skill Learning under Environment Evolution for Web Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33528 - Scaling Verifiable Environments for Long-horizon Work Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04906 - SimulSense: Sense-Driven Interpreting for Efficient Simultaneous Speech Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.21932 - EnvLunch: The Environment as a Free Lunch for Learning to Interact Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33817 - AdaTutor: Adaptive Tutoring through Pedagogical Strategy Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34659 - A Contextual Measure of Ambiguity in Prescriptive Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35461 - Hey, guess what: CUES lead to inferences about typicality Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33239 - Write What Matters: Disentangling Token Selection from Slot Allocation in Recurrent Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34180 - Perturbation-Based Data Selection for Medical Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33440 - How Firm Are AI Models' Ethical Boundaries? A Pay-Stub Editing Test of 15 Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30751 - Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.06164 - When the Weakest Language Keeps Moving: ARMOR-DP for Multilingual BabyLM Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33583 - LLMs Can Tackle High Energy Theoretical Physics, yet Gaps Remain: Part I, Quantum Field Theory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33134 - The Voice on the Line Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35272 - Text Is the Bottleneck: A Small-Scale Replication of LLM Game Playing in Riichi Mahjong Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34791 - Meta-CLIP: Metadata-Conditioned Contrastive Learning for Zero-Shot Disease Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33674 - Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18639 - Advancing the Pareto Frontier of Test-Time Scaling with Multi-Path Plan Aggregation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.11620 - LLM-as-a-Judge Version Shift: The Instrument Changed, Not the Standard Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32986 - 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 - Pancasila-Dilemmas: Evaluating Large Language Models on Indonesian Human Value Dilemmas Grounded in Pancasila Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18066 - Dummy Backdoor as a Defense: Removing Unknown Backdoors via Shared Internal Mechanisms for Generative LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11648 - Cross-Loop Query Handoff: How Later Loops Redirect Two-Hop Retrieval in the Ouro Looped Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34639 - CalibraRL: Confidence-Calibrated Reinforcement Learning for Mitigating Hallucinations in RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35142 - AfriGuard: Safety and Robust Refusal For African Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26474 - LangMAP: A Language-Adaptive Approach to Tokenization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23566 - MATCHA: A Chinese Multi-Disorder Mental Health Dataset with Cross-Lingual Analyses on Social Media Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35512 - Recursive Semantic Divergence for LLM Agent Consistency Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33012 - Diagnosing and Mitigating Long-Session Degradation in Full-Duplex Speech Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34991 - Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01631 - Reinforcement Learning Done Right for Explicit Confidence Targets Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35059 - TellOnce: Correcting Coding Agents Once, Improving Their Future Actions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13174 - Rethinking Evaluation for Principled Generalization Using a Kripkean Challenge to Meaning as Use Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35111 - Representation-Aligned Auxiliary Supervision for Language Model Adaptation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04098 - ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11212 - Automated, auditable dating of the Babylonian Astronomical Diaries with language models and astronomical tools Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34297 - Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27309 - How Reliable are AMR Parser Outputs? Uncertainty Estimation for AMR Parsing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13236 - The Lay of the Land in Idiom-Translation Quality Estimation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35261 - Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00326 - Where LLMs Fail with Visualization DSLs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01873 - Mechanistic Insights into LoRA: Layer Sparsity for Adaptive Fine-Tuning via Path Patching Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34756 - Beyond Vision-Language Models: Visual-Semantic Affect Graphs for Emotion Recognition in Artworks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35244 - Mycelium: A Meta-Study of Hallucination Detection Across Provenance, Typology, and Granularities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33608 - Whispers from the Neighbors: Rethinking Caption Consensus as Inference-Time Evidence for Vision-Language Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33798 - Veracity labels flip the emotional tone of language models but leave racial disparities intact Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33021 - HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31179 - OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05843 - Dual-Slot: From Serial Loops to Parallel Slots in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25086 - SRA: Selective Residual Adaptation for LLM Reasoning Enhancement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34199 - Omni-InteractScope: Benchmarking Proactive and Agentic Interaction in Continuous Omnimodal Streams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35439 - AlphaCNOT: Learning CNOT Minimization with Model-Based Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13812 - Evaluating Harmful Memorization in LLM Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.02296 - C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34961 - GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09921 - CIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14386 - AI Teaches Humans to Handle Complexity in the Game of Go Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33323 - Critic's Eye: Review-Grounded Graph Reasoning for Long-Form Motif Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35011 - PhaseBreak: Proactive Temporal Protection against Unauthorized Image-to-Video Animation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33070 - A Distribution-Matching Perspective on LLM Training Algorithms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33740 - CoDeRNet: Selective Cross-Task Routing under Heterogeneous Supervision for Change Detection and Captioning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34876 - Proof-of-Agentness: Towards Verifying Agents on the Web Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35288 - Conviction Without Evidence: Verdict Stability Is Independent of Visual Grounding in Medical Vision--Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34520 - A Battery for AI Propensity Measurement: Rubrics, Synthetic Item Banks, and Annotations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34614 - A Canary in the Neural Mine: Catching an Image Classifier's Silent, Confident Failures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33063 - GPT4o-Receipt: A Dataset and Human Study for AI-Generated Document Forensics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11442 - AgentProofBench: Benchmarking Reusable Verifiers for Web Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34634 - DecoyCount: Evaluating Visual-Reasoning Misalignment in Counting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34855 - Error-Subspace Calibration for Multi-Task Model Merging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33483 - Health-SCORE: Towards Scalable Rubrics for Improving Health-LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.18706 - Operationalizing Governed Agentic Workflows in Regulated Finance: A Customer Zero Case Study using Zafin AIOS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33253 - Governing Enterprise AI Traffic at Scale: Design and Operation of a Policy-Driven, Multi-Vendor LLM Gateway on Envoy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35509 - SceneAgent: An Agentic Pipeline from 3D and 4D Captures to Simulation Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34745 - Beyond 0-100: How Confidence Scale Design Shapes Verbalized Confidence and LLM Metacognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09309 - The Target Agent Is Its Own Best Critic but a Poor Proposer: Self-Improved Red Teaming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34965 - VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34717 - TRIAGE: Efficient Vision-Language-Action Inference Needs Both Reuse and Pruning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34519 - Beyond Federated Learning: Decentralized Agentic Systems for Self-Evolving Clinical Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35453 - Reva: Real-Time Vulnerability Detection through Contextual Probing of Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35829 - Feature Scaling Beats Architecture Choice in Offline Respiratory Screening for Low-Resource Clinics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33030 - Logic Hijacking of RAG: Single-Document Poisoning via Local Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34829 - Evaluate the Stack, Not the Layer: Do Deterministic and LLM Gates for Agent Actions Fail Independently? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07359 - PhysEvolve: Verifier-grounded Self-evolution for Physical Reasoning with Executable Worlds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34921 - EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35690 - ACSAN: All-Convolutional Self-Attention Network Integrating Convolutional Operations with Vision Transformer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35375 - Locked In: Multi-Objective RL for the AI Data Center Build-Out Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35147 - ReGE: Stronger Agents through Experience Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33861 - Pretraining Knows What, Simulation Teaches How: Compositional Generalization in a Sim-Trained Robot Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35817 - Scaling Qualitative Analysis with Large Language Models: Development and Validation of the Smart Coder Framework for Human-LLM Collaborative Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33205 - AgentOrch: How Close Can Global Orchestration Come to Step-by-Step Interaction? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33375 - An actively trained neural operator for near-explicit atmospheric chemistry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33771 - Distilling Expert Judgment at Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33233 - SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27703 - Agents for Experiments, Experiments for Agents: A Design Grammar for AI-Enabled Experimental Science Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17746 - From Single Spins to Ensembles: A Calibrated Symbolic Regression Pipeline for NV Spectroscopy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35016 - Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28876 - Benchmarking Obstacle-Conditioned Safety in Household Robot Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34674 - ProbeID: Verifying MCP Tool Identity for LLM Agents under Registry Drift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33633 - E3tereo: Improving Stereo Matching at Depth Boundaries with Learned Geometric Edges Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33704 - Energy Efficient Lung Tumor Segmentation with a modified CBAM ENet Skip Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33479 - The Right Fact, the Wrong Decision: SciValidityBench for Scientific Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34767 - AlphaIdeaBench: Benchmarking Automated Research Idea Generation under Feasibility Constraints with Peer Review Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33644 - A Diagnostic Protocol for GNNs in Electricity Load Forecasting: Separating Parameter Sharing from Neighborhood Access Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35074 - CAFE: Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16435 - GEMS-RAG: Graph-grounded Engineering Multimodal Standards Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33277 - Gangqinpu: A Multi-Genre, Multi-Task Piano Dataset with Aligned Audio, MIDI, and Musical Scores Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34694 - Generative Structure from Motion with Native 3D Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35522 - SearchHorizonBench: A Benchmark for Search Value in AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34714 - Centralized Critics for N-Agent Ad Hoc Teamwork Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34799 - Subspace Crystallization in Grokking: Rank Compression Tracks the Phase Transition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35112 - Arya Forge: Auditing Validation and Release Approval for Financial Instruction Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34778 - CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34722 - MultiEvoSkill: Structure-Aware Multi-Agent Skill Evolution for Generalizable Skill Artifacts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34260 - Joint Latent Reasoning and Observation for Agentic Video Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35229 - Precedence-Aware Resource Allocation: Extending the AUTOC Framework to Multi-Level Treatments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34812 - Learning When to Collaborate: Selective Multi-Agent Medical Reasoning via Uncertainty-Aware Routing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33544 - Faithful Explanations under Missing Modalities in Multimodal Dementia Prognosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35430 - Satellite Intelligence: Distributed Training, Collaborative Inference,and LLM Adaptation in LEO Constellation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35282 - AgenticCity-Bench: Longitudinal Multimodal Observations of Urban Dynamics with Agentic Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35293 - Rectified Language Flow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33811 - Can Agentic Code Review Catch Vulnerabilities Before They Are Merged? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33509 - MatOS: An Agent Operating System for Materials Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34203 - NeSySpec: Neuro-Symbolic Technical Intelligence for Auditing Engineering Specifications with an Application to Aircraft Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35403 - Reasoning Patterns for Efficient AI Coding: An Empirical Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34943 - MulFCoder: Framework-conditioned Multi-agent for MLLM-based Multi-framework Front-end Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.34418 - Generative AI in Turbulence: Foundations, Applications, Validations and Benchmarks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35123 - A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33318 - Build or Adopt? Custom-Built vs. General-Purpose LLM Agent Harnesses for Automotive GUI Testing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33636 - Exploring the Limits of Large Language Models as a Reflection of Human Cognition: An Illustration in the Context of Moral Judgement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.06950 - Zero-Shot Multi-Class Wafer Map Classification with Rule-Ordered Prompts for Large Multimodal Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35080 - MOSHO: A Native Discrete Shark-Inspired Metaheuristic for Hardware-Aware Neural Architecture Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33358 - Counterfactual Model Testing Under Distribution Shift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33594 - OTel: Open Telco AI Datasets, Benchmarks, and Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07766 - LE-GDA: Layer Ensemble Gaussian Discriminant Analysis for Training-Free Few-Shot CLIP Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34901 - Power-of-Two Leaky Integrate-and-Fire Neurons for Event-Driven Vision-Language-Action Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33658 - PatentAgentBench: Benchmarking LLM Agents with Professional Patent Task Suites Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35031 - The Physical Cost of Context: Quality-Constrained Resource Accounting for Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34763 - Recovering Wasted Compute in Autoresearch Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10424 - The Impact of Personalized AI Response Suggestions on Content Creators' Direct Messaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34770 - AutoB2G: Agentic Simulation and Reinforcement Learning for Spatio-Temporal Grid-Interactive Building Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26005 - Physics-Informed Graph-Based Safe RL with Constraint-Specific Critics for Community Battery Coordination in Distribution Network Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33654 - From Outranking Flow Scores to Linear Programs: Group Decision Making in PROMETHEE II Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34481 - From Hype to ROI: An Economic Model for LLM Adoption in Information Systems and Security Operations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33352 - VaLoP: Value Gradient Lookahead and Pullback for Reward-Guided Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35607 - Autonomous Structural Discovery Of Bioprocess Dynamics And Kinetics Via LLM-Driven Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35391 - Deep Scientific Reasoning under Physical Constraints: Structure-Aware Spectrum Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34021 - A systematic evaluation of vision-language models for observational astronomical reasoning tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.24589 - GADAR: Generalizing Across Domains via Action Ranking for Classical Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34868 - CORMA: Constraint-Routed Decision Mamba for Generalizable Multi-Constraint Offline Safe Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34208 - Multi-Fidelity Training Reshapes Uncertainty Decomposition in Atomistic Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35560 - Neutral Substrates: A Design Constraint for Shared Records Under Persistent Interpretive Disagreement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.14271 - AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33245 - VLMProbe: An Open-source Library for VLM Probing and Interpretation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33072 - RadOnc-Agent: An Integrated Framework for AI Workflows Across the Radiotherapy Care Pathway Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06923 - Geometry Meets Physics: Data-Efficient Pre-Training for Unstructured Neural PDE Solvers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03363 - UTA: Universal Training Adaptive Learning Rate Decay Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35113 - CyberDual: AI Attackers versus AI Code Reviewers in Real Software Maintenance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34435 - An Interactive Evolutionary Multiobjective Optimization Algorithm Based on Interpretable Active Preference Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35470 - TrustJev: Separating Policy Authority from Untrusted Evidence in LLM-Based Decisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34826 - Scope-Gap Injection: Exploiting Evaluator Channel Blind Spots in the OpenClaw Agent Security Competition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34777 - DRA-SAM: Disagreement-Driven Referential Active SAM for Low-Altitude Drone Referring Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33057 - Efficient Generation of Diverse Cooperative Agents with World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.07450 - VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29483 - Graph-dependent pooling: adaptive granularity in hierarchical graph neural networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33623 - CTXAgent - Self-Controlled Context Management of LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34425 - SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19842 - Certifying Distributionally Robust Decisions from Projection Observations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34493 - Why Are LLMs Confidently Wrong? Correcting Overconfident Errors via Causal Head Intervention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34994 - Sparse Recovery Bird's-Eye View Model Soup for Robust Camera-Based 3D Object Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34976 - Learning Force-Reactive Humanoid Loco-Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35862 - A Unified Arena for LLM Agents across Diverse Eurogame Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35773 - Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22168 - AutoPRL: Automated Path Representation Learning via a Learnable View Generator Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35032 - Extraction meets Distillation - cryptanalytic techniques to recover parameters from a Deep Neural Network Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33671 - Dynamic Multi-Step Decoding for Time-Series Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34409 - Numina Fuse: Interactive Autoformalization in Lean 4 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33860 - Patient-specific rubric-based evaluation of large language models across longitudinal cancer care Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35847 - Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30383 - LLM-Enhanced Heterogeneous Graph Learning with Business Semantics for Financial Fraud Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35298 - RepoTrace: Improving Requirement Tracing in Multi-Round Agent Interactions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35333 - RIDE-Splat: Reflection Removal for In-the-Wild Driving Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34632 - JRDB-AVR: An Active Visual Reasoning Benchmark for Embodied Agents in Real-World Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35032 - DairySocialTwin: Auditing the video-to-graph evidence chain in cattle social networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32989 - Prefetch-Steered Routing: Deterministic Cache-Aware Expert Selection for Offloaded Mixture-of-Experts Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34721 - Explainable Multimodal AI Approach to Reduce Unnecessary Breast Biopsies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35704 - Adapt for Planning, Not just Prediction: Optimistic Test-Time World Model Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35636 - A Comprehensive Framework for All Stages of Large-Model Training: From Data and Tokenization, through Pretraining, to Post-Training Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33451 - Beyond Behaviour: A Stimulus-Response Safety Evaluation of Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34837 - POD-RoPE: Rotary Position Encoding over Physical Observation Distributions for Embodied AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33745 - DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08614 - Oddin: Latent Visual Reasoning in Unified Multimodal Models via Self-Distillation from Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33062 - A Framework for Automated Multi-Source Satellite Data Analytics and LLM-Based Report Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05625 - LongSearchEval: Evaluating Long-Horizon Web Search Capabilities of Large Language Models via a Trajectory-Aware Agent Framework with Failure-Node Localization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35150 - PACE: Research Proving Agent for Adaptive Conjecture Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33690 - StaX-Net: Stackelberg Interleaved Asymmetric Network for Cross-Modality Medical Image Translation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34214 - Babysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34748 - Memory or a Clock? Auditing a Memory Advantage in XLand-MiniGrid with Seeds, Maps and Evaluation Noise Apart Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33816 - How To Build A Modern Diffusion Language Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33391 - EOPSA: Efficient On-Policy Self-Distilled Safety Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34519 - From Pixels to Prompts: Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07544 - JANUS: Synthesizing Cross-Layer Defenses Against Web Deserialization Attacks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35532 - LLM-Augmented Agent-Based Simulation of Cyber Social Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32988 - C-DFF: Concept-Level Diagnostics for Mechanism Parity in Simulation-Based Validation of Autonomous Driving Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33760 - One-Shot Federated Model Editing for Device Dynamics at the Edge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35212 - InfiniteWorld: Separating Visual Evidence from Familiar Physics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33777 - From Speech Tokens to Stolen Voices: Attacker-Chosen-Text Speaker Impersonation via Representation Inversion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34688 - ShutdownMod: Turning Any Trajectory into a Shutdown Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35486 - GUIFlow: Temporal Redundancy-Aware Incremental Inference for GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34959 - SkillLifeBench: Benchmarking Security Across the Lifecycle of Agent Skills Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35215 - KAPPA: Checking the Proofs in Statistics Papers with Lean 4 and Language Model Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35596 - I-HITL: Inalienable Human-in-the-Loop Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35835 - OptiCom : A Unified Framework for State-Conditioned Composition in LLM-Driven Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37221 - 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 - Ranking Function Generation with LLMs for Termination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35523 - Query-Driven Learning for Lifted Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34747 - Learning What to Share: Expert Specialization for Time-Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33822 - Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08241 - Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24064 - MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08327 - Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35193 - Exploring Joint-Embedding Predictive Architectures for Self-Supervised Representation Learning of Powder X-ray Diffraction Patterns Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33310 - Cross-Platform Application Migration to HarmonyOS: An Agentic Pipeline with Artifact-Derived Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33197 - Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34298 - Rank-1 Weight-Corrected Trainable Weight Averaging for Out-of-Distribution Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33909 - CLOSURE: Cross-Channel Closure for Multivariate Time Series Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35753 - ConMem: Counterfactual Multi-Scenario Probing for Resolving LLM Memory Misalignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33432 - EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28197 - SWE-Ladder: Learning to Localize, Reproduce, and Patch via Progressive Privileged Self-Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33667 - Silent and Costly: Characterizing and Detecting Prompt-Caching Mis-Integration in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34817 - TAD: Distilling Vision-Language-Action Policies from Teacher Trajectories Alone Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33650 - Diagnosing and Mitigating Evidence Misgrounding in Multimodal Knowledge Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33075 - AnalogPortBench: Benchmarking LLMs on Analog Circuit Porting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33088 - AIPC: Evidence-Guided Agent Workflows for PyTorch Project Deployment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34890 - Estimation of Propagated Risk in LLM-based Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33282 - Retriever-Free Retrieval: Navigating Documents with Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35868 - ProMo3D: Probing Motion Cues in Frozen 3D Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33802 - Free to Look, Free to Reason: Simple LLM Harnesses Outdiagnose Hand-Crafted Root Cause Analysis Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35767 - CoEvolve: Counterfactual-Guided Co-Evolution of Memory and Collaboration in Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33539 - CounterFlow: Target-Conditioned Flow Matching for Visual Counterfactuals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35679 - RobotAgentBench: Towards Open-world Robot Autonomy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34649 - HobbyLM: A Sparse Mixture-of-Experts Model Family on a Hobby Budget Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34582 - All the Facts, Still the Wrong Answer: Integration Gaps in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33764 - Evolve on Graph: Self-Evolving Knowledge Graph Reasoning without Question Annotations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35598 - Topic-Level Fairness in Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34683 - V$^3$AST-Bench: Verifiable, Valid, and Versatile Safety Evaluation for Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35188 - Beyond Physical Illness: Can Clinical Narratives Reveal Emerging Mental Health Risks in Chronically Ill Patients? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35761 - Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33845 - Decision Model Factory: Building Specialized Sovereign Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34956 - SPARTA: A Sparse Ternary LLM Accelerator with Adaptive Attention and Unified Datapath for Long-Context Edge Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34824 - RSIV-Harness: A Recursive Self-Improvement Harness Framework for Open-Domain Conversational Text-to-Visualization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35316 - TrySee: Modular Perception-Enhanced VLM Grounding for Closed-Loop Robot Task Planning in Specialized Domains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35687 - Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35138 - ExCal: Optimization-Free Multivariate Time Series Anomaly Detection via Excess Calibration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35568 - WorldFailBench: Do World Models Understand Policy Failures? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33565 - Benchmarking System One Models for Time-Series Decision Making: A Case Study of Jev Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33410 - Pacifo: An Efficient Fully Homomorphic Encryption-based Lightweight ResNet for Trustworthy Machine Learning as a Service Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33525 - The Agent in the Middle: How AI-Mediated Access Reshapes Web Vulnerability Exploitation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35541 - Exact Unlearning After Data Curation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33426 - BoardSafety: AI-Ready Data from Manufacturer Documentation for Development-Board Safety Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33448 - LLM WikiLeaks: Uncovering URL-Based Capability Extension and Security Circumvention in Agentic Message Boards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34542 - AliO: Output Alignment Matters in Long-Term Time Series Forecasing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11213 - MedEvo: Medical Reasoning Evolution through Knowledge Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17690 - Steering the Teacher: Improving On-Policy Self-Distillation for Thinking Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34005 - SEEK: Skill Extraction with Evolving Knowledge against Frontier Science Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34365 - AGQ: Action-Guided Ultra-Low-Bit Quantization for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33074 - ProtoEEG: Structured Prototype Alignment for EEG Visual Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33065 - Evaluating Visual Language Models on Visual Grounding for Visually Impaired People Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33078 - Relational Composition as Parallel Transport: What Per-Entity Frames Force in Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34945 - The Future Is Finer: Multivariate Time Series Super-Resolution Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33470 - GMoE-FTI: A Universal Facial Template Inversion Method Adopting Genuine Mixture-of-Experts Mechanism Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33055 - OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35684 - MarineLife-16K: An Attribute-Rich Video-Text Dataset for Motion-Aware Marine Video Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33478 - The As-If Machine: Personalized counterfactuals make distant policy risks feel close Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33301 - Hierarchical Task Network planning in the Goal Lifecycle Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34668 - RAQ-MLA: Role-Aware Quantization for Multi-Head Latent Attention Caches Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33625 - Acute Stroke Classification Using Asymmetric Data Standardization and Orthogonal-Focal Loss Optimized CNN-ViT Cross-Attention Fusion: A Multicenter External Validation Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34529 - TempShap: When and How Much a Feature Matters in Time-Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33330 - Recursive Reasoning or Statistical Extrapolation? In-Context Learning in Multi-Agent Interdependent Decision-Making Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18591 - The Hidden Costs of Forgetting: A Study of Trajectory Deletion in Software Engineering Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35496 - Infinity Machine: a self-improving AI agent for research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35579 - FlashScript: Compiling Recurring Agent Workflows into Reusable Neuro-Symbolic Programs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33876 - IRON-Meme: A Benchmark for Structured Understanding of Identities and Roles in Online Meme Narratives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33097 - Inverse Modeling for Laser Pulse Shape Design in Inertial Confinement Fusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33096 - Agentic Algorithm Design: LLMs that Propose, Formalise, and Prove Runtime Bounds for Evolutionary Algorithms in Lean Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35595 - A Sign Law for Entropy Drift under Sampler Mismatch in RLVR Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34044 - Image Clustering with Vision-Language Model Embeddings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33265 - Provably Efficient Q-learning for Robust Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35656 - Spatial Audio Generation and Editing with Executable Plans and Self-Distilling Transfusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34415 - Local Entropy Fluctuations for Black-Box LLM-Generated Text Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33767 - Agentic AI Orchestration Framework for Spatial Intelligence: Supply Chain Deployment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34569 - Responsibility Boundaries for Agentic Systems: A Comparative Evaluation of Probabilistic Agentic Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33312 - Curriculum-Guided Acquisition of Hierarchical Task Knowledge from LLM-Generated Experience Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34677 - Reward-Guided RRT* for Budgeted Task and Motion Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35289 - Beyond Single-Attribute Auditing: A Configurable Multi-Attribute Benchmark for Intersectional Fairness in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35069 - Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15772 - SlowLab: Benchmarking Autonomous AI Agents on a Year of Experiments They Cannot Undo Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34644 - ComBeautify: Leveraging Code Change Summaries for Conventional Commit Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34374 - RADAgent: Automating RADseq Pipelines with Private Open-Source LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33009 - CaliMem: Search-Efficient Data Agent via Calibrated Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34500 - Waypoint: Analytically Modeling GEMM for CPUs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34914 - Toward Fast Human Reaction Modeling from High-Frequency Digital Interaction Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35079 - Unlocking the Specialization Capability of PPG Foundation Models for Wearable Signals through Structured Pruning and Adaptive Fine-Tuning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33788 - NameTrap: Steering AI Coding Agents Toward Security Vulnerabilities via Variable Names Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34253 - Recursive CLIP: Vision-Language Distillation with Looped Transformer Blocks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34563 - KDHNet: A Knowledge-Driven Hybrid Network for Limited-Calibration SSVEP Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33058 - Multitask Interactions in Recurrent Dynamics across 100 Cognitive Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33926 - In-Context Adapter Generation for Compositional Generalization in Large Audio Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34413 - ClinVerse: A Realistic Multi-Agent Diagnostic Environment for Training and Evaluating Medical Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34878 - Human-Feedback-Guided Multi-Agent Inverse Reinforcement Learning for Interactive Driving Behavior Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33726 - LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33470 - DROA-CLIPSeg: Prompt-Guided Thin Crack Segmentation in Low-Light Conditions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33635 - WebViSE: Scaling Visual Design Intelligence from the Open Web for LLM Website Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33929 - ArbiGraph: Arbitrarily Scalable Verifiable Task Graphs for Evaluating Context Management Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20764 - DoubleFree:Exploiting Exploration History for Rollout-Free Multi-Task LLMs Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34272 - InferPriv: Evaluating Inferential Privacy Leakage in LLM Assistants Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34640 - CFL-aware edge design for graph neural solvers of hyperbolic transport Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33769 - OrthoRF: Exploring Orthogonality in Object-Centric Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35203 - How Much Information Can We Fit inside a Transformer? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34553 - More: Mode-Optimized Reasoning with Self-Adaptive Effort for Self-Evolving Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33684 - Whale You Go Green? Immediate and Longitudinal Effects of Embodied Conversational AI Avatars on Sustainable Behavioral Tendencies and Pro-Environmental Attitudes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33191 - Agentic AI Empowered Intent-Based Networking for 6G Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2601.06640 - AdaTrendLike: Adaptive Hierarchical Detrending and Trend Likelihood Scoring for Time Series Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35400 - LegoSR: A Unified Framework for Self-improving Agent-Guided Scientific Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33465 - MOSAIC: Towards a Universal Latent Space for Computational Pathology Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33059 - GRASP: Group-Adaptive Hybrid RL-SFT Post-Training for Medical VQA without Reasoning Annotations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34561 - Strategic Calibration in LLM Multi-Agent Systems: Audited Pivot Scoring for Truthful Elicitation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33728 - Stop or Clarify? Experience-Conditioned Active Fact Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34941 - Audio-R1: Audio Reasoning through Reinforcement Learning on Self-Supervised Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34609 - Developer Task Delegation to LLMs and the Trust Factor: A Mixed Methods Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34317 - Streaming Recurrent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34833 - Profiling a Frontier Agent with EBench: From Direct Control to Harness with Policy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35832 - ArchiveLens: A Generative Spatial Knowledge Framework for Semantic Reconstruction of Historical Maps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35606 - SRHarness: A Harness for Agentic Symbolic Regression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35501 - A Unified Analysis of Importance-Corrected Momentum Actor-Critic over a Markovian Trajectory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33477 - ICCU: In-Context Continual Unlearning via Pattern-Induced Refusal Rules Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27138 - Variational Cognitive Memory Abstraction for Long-Horizon Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34251 - Intervene, Calibrate, Discover: Learning Causal Structure from Pixels Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34711 - Closing the empirical loop: autonomous AI agents conduct end-to-end research with human participants Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.13421 - Artificial Intelligence in Mechanical Engineering: Foundations, Opportunities, Challenges, and Responsibilities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33105 - Uncovering the Turing Test's Latent Signal: Indistinguishability as a Reward Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34781 - Should Pseudo-Labels Share Mini-Batches with Labeled Examples? Semi-Supervised Continual Active Learning with Limited Training Cost Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35345 - Improving Instruction Hierarchy by Learning from Goal-Goal Conflicts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35093 - Formal Explanations for Linear Temporal Logic over Finite Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35169 - Joint Dynamic Lane Reversal and Variable Speed Limit Control: A Graphormer-Based Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35070 - QECGBERT: A Scalable ECG Foundation Model Based on Self-Supervised Language Learning via VQ-VAE Waveform Tokenization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33964 - OS-Wizard: Scaling Computer-Using Agents to Specialized Software via Knowledge-Guided Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33907 - CSI-TextBench: A Dataset and Benchmark for Language-Grounded Ambient Sensing Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34616 - Repairing Broken Access Control in Web Applications with LLMs: An Empirical Benchmark Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34290 - NewsBench: Expert-Grounded Evaluation of Epistemic Quality in AI News Reporting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33240 - Multiscale Policy Optimization for Long-Horizon LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35013 - EEGaze: Multimodal Attention Prediction in Visual Search via EEG-Based Saliency Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35757 - AOS-Bench: Can LLM Agents Manage Dynamic Workloads? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33178 - Shared-Factor-Conditioned Diffusion for Low-Rank Tensor Recovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35368 - SKALOS: Learning to Distinguish Similar Skills with Capability Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34728 - Application of Artificial Intelligence in the Management of Climate Change-Related Health Issues in Africa Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35294 - A Computer Vision Approach to Visual Fraud Detection in Phishing Websites Using YOLOv8 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34015 - MARC: Mechanism-Aware Reflective Correction for Articulated Object Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33060 - Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34638 - Aerial-R1: Reinforcing Aerial Reasoning and Segmentation in MLLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33056 - SHIFT-JEV: Certified Abstention and Gain-Gated Continual Adaptation for LLM-Based Decision Models under Distribution Shift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34329 - XPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02438 - Collective Emergent Alignment: Measuring and Amplifying Interaction-Induced Reasoning Alignment in Multi-Agent LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34836 - How Do Coding-Agent Harnesses Self-Evolve? An Empirical Study of Retrospective Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34938 - Video World Models Need Predictable Latents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34663 - EGGPlacer: Energy-Guided Generative Chip Placement with Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33099 - Replicate What Varies: Resource Sharing for Domain-Randomized Embodied Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33582 - EvolveMAS: A Unified Self-Evolution Framework for Decentralized Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34450 - NGM: A Plug-and-Play Training-Free Memory Module for LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16893 - Agents That Edit Documents: Measuring Agentic PDF Forgery Against a Non-Agentic Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23953 - Seeing the Options: Typed Decisions over Visual Candidates with Reusable Option Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33702 - Game theory of academic effort and hiring in the age of AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35802 - ToDoPro: Faster and Better Reference-Based Generation: Early Token Reduction via Downsampled Self-Probing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34782 - Test-Time Confidence Adaptation under RL-Induced Trajectory Shift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35500 - Hybrid-time PINNs: Discontinuity-Aware Physics-Informed Neural Networks for Learning Hybrid Dynamical Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33562 - Recovering Black-Box Point Cloud Models from Pose Shifts via Derivative-Free Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34850 - From Language to Drives: A Multimodal Framework for Aligning Autonomous Robots with Human Purposes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35629 - Extended LASMP: Language Aided Subset Sampling Based Motion Planner for Drone Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34054 - 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 - Learning Counterfactual World Models for Embodied Reasoning under Partial Observability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05834 - Context Is Not Free: Carbon-Aware LLM Routing for Multi-Turn LLM Web Services across Geo-Distributed Data Centers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35230 - Beyond Static Structures: Linking Protein Dynamics to Function via DynaReason-Pro Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33804 - EEGBiFormer: Real-Time EEG Attention Classification via Hybrid CNN-Transformer with EEG-Informed Auditory Protocol Validation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33832 - Latent Goal Prediction from Language for Model-Based Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20627 - Adapting DNNs to Embrace Voltage Scaling Induced Errors via Accumulation-Aware Quantization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33824 - LLMs in Cloud: A Discussion on Architecture, Orchestration, and Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33475 - Single-Cycle Battery Remaining Useful Life Prediction with Compressed Continuous Wavelet Features and Deep Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34159 - Are We Done with UMLS Injection into Language Models for Medical Question Answering? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33801 - AutoEnergyDesign: An LLM-Driven Agent for Automatic Energy System Design Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35160 - MuSID-KD: Multigranularity Knowledge Distillation for Generative Recommendation with Semantic IDs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35218 - Efficient Exact Unlearning for Federated Zeroth-Order Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35211 - Scoped Semantic Invariance as a Foundation for LLM Reliability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33267 - Hierarchical Cooperative GFlowNets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33968 - Movable-Element Multi-Functional RIS-Assisted Hybrid RSMA-NOMA: A Constrained Hybrid Reinforcement Learning Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34701 - HumanoidNDM: Closing the Training-Deployment Gap of Motion Tracking via Humanoid Neural Dynamics Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34126 - DISCERN: Can AI Agents Work Like Scientists and Guide Discovery? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33357 - When Generated Information Returns: Error Persistence in LLM-Mediated Information Ecosystems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33617 - Optimal Correction Sets for Provable Redress of Contestable Causal Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33138 - Fed-Universe: A Semantic-Geometric-Topological-Human (S-G-T-H) Stack for Negotiated Alignment in Federated Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34009 - Before Blaming the LLM, Diagnose the Workflow: A Role-Level Difficulty Profile for Translating Natural Language into Ontology-Grounded Statements Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35267 - SentryBench: A Cost-Sensitive Benchmark for Adversarial Robustness of Tool-Using LLM Agents in Public-Safety Deployments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34535 - Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33732 - RoboReason: Boosting Robotics-Relevant VLM Reasoning Through Scalable Data Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33778 - Data Governance for Generative and Agentic AI : Technology, Law, Economics, and Security Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33605 - Geometric Consistency Based Label-Free Validation for Checkpoint Selection in Audio Active Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35329 - Multi-Objective Reinforcement Learning Using Routed Ensembles and Trajectory Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35733 - SAP-ViT: A Self-Attributing Patch Vision Transformer for Medical Image Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35593 - When Does Pre-Trained Capacity Help Causal Learning? From Scalar Prediction to Counterfactual Post-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33311 - Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14494 - Isharah-Selfie: Continuous Sign Language Recognition Dataset for One-handed Signing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33200 - FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35744 - Auditing evaluation artifacts and data leakage in large language model systems for rare disease diagnosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33592 - MarkovSim: an LLM Agent Harness with Bounded Context for Long-Horizon Computational Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35349 - Same Story, Different Lens: A Multi-Agent System for Cross-Outlet News Framing Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35208 - Safe by Benchmark, Unsafe in Practice: Lessons from 1331 Child-Related AI Incidents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34705 - CANS: Capability-Preserving Neuron Steering for Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35530 - Holding a Steady Course: Knowledge Evolution from Expertise and Lessons for Continual Agent Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34043 - FraudSociety: A Generative Agent-Based Society for the Financial-Fraud Economy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33536 - Decoupled Prune-and-Reconstruct: Training on a Compact Core with Double-Layer Sparsification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34140 - BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33355 - Rethinking Verification in Agent Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34577 - CodeMeepo: A Multi-Agent Workflow for Repository-Level Code Migration and Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34633 - Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03195 - How Humans Learn Unfamiliar Worlds: A Think-Aloud Dataset on ARC-AGI-3 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34523 - Self-Supervised Pretraining for PHM: What Transfers, What Does Not, and What Federating It Costs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35280 - ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34386 - Thinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34654 - Multi-Agent Debate for Belief Optimization in Defeasible Domains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12718 - BriLLM-MetaPred: A Representation-Prediction Unity Language Model with Adaptive Self-Measurement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34018 - R2A-Sales: A Policy-Atom-Matched Benchmark for Rule-to-Action Gaps in Goal-Directed Sales Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34185 - EvoBench: An Evolving, Diagnostic Benchmark Framework for Environmental Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35464 - Belief-Conditioned Multi-Agent Actor Critic for Decentralized LLM Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35398 - UniGFM-RAG: Unify Graph Foundation Models and Large Language Models for End-to-End Retrieval and Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34866 - ProtAgent: Post-Training Compact Protein Tool Agents with Interaction-Level Credit Assignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33746 - Data Optimization for LLMs: A Survey Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33405 - Bridging Static and Agentic RAG for Taiwanese Historical Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23056 - Outcome-Aware Agents: When Does Causal Structure Help a Forward Model Foresee the Consequences of Actions? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34385 - Audit Where Hacks Pay: Budgeted Strong-Verifier Audits Against Reward Hacking in GRPO Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35716 - The Watchtower Imperative: Lifespan-Calibrated Evaluation for Frontier AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35725 - From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34094 - Measurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00794 - Beyond Correctness: Attribution of Natural-Language Documentation for Formal Libraries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33094 - SoK: Timestamps Are Not a Time Model: Rethinking Temporal Reasoning in Host-Based Intrusion Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35151 - Harness-Model Collaboration for Long-Horizon Continual Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34724 - PREFER: Personalized Review Summarization with Online Preference Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05911 - Conformance as a Distribution: Delegation Contracts, Error Budgets, and the Allocation of Evaluation Authority in Use-Based AI Regulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33112 - From Denoising Dynamics to Endpoint Uncertainty in Diffusion Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35425