TILens Daily Edition 2026-10-13 Filters: topic=ai-research, github=hidden Stats: 435 articles, 5 sources, 430 research papers Top topics: AI Research, AI, Python ## News - Q4 TNA Email - Muse Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/q4-tna-email-muse/ - Google’s Playground Turns Prompts Into Games. Can It Build an Audience? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/google-playground-unity-spark-ai-games/ - 😺 Meta’s Muse Wonder is here, priced like Opus Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/meta-s-muse-wonder-is-here-priced-like-opus-ee30/ - AMD’s Helion Could Change the Cost of Running AI Agents Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/amd-helion-ai-agent-operating-costs/ - AI Weekly Issue #537: AI models may soon copy themselves onto smart fridges, Anthropic says Source: ai-weekly Topic: AI (+AI Research) URL: https://aiweekly.co/issues/ai-models-may-soon-copy-themselves-onto-smart-fridges ## Research - Your Agent Doesn't Need More Freedom Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/your-agent-doesnt-need-more-freedom/ - Three Samplers, One Posterior: NUTS vs. Emcee vs. Nested Sampling Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/three-samplers-one-posterior-nuts-vs-emcee-vs-nested-sampling/ - Coding Agents Can Solve the Task — But How Much Work Did They Waste? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/coding-agents-can-solve-the-task-but-how-much-work-did-they-waste/ - How to Leverage NLP for Product Data Science Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-leverage-nlp-for-product-data-science/ - Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.01025 - Evo$^2$: Evolving the Evolver through Weight-Harness Co-Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13025 - Evaluating LLM Creativity through Long-Tail Performance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12998 - PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13171 - BenCoDiC: A Large-Scale Contextual Cyberbullying Corpus for Bengali Political News Discourse FULL VERSION Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13121 - Revisiting Accent Classification with DistilHuBERT: Speaker-Disjoint Evaluation and Cross-Corpus Generalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13440 - O\'ido: Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural Accelerator Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13447 - CAST: Credit Alignment for Cross-Tokenizer On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13257 - From 2.1M Hours of Raw Broadcast Audio to Finnish Speech SSL: Confidence Filtering and Architectural Analysis at Scale Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13102 - Test-Time Memory Construction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13348 - A generative-informed neuro-symbolic framework for syntactic ambiguity resolution: Evidence from Arabic DPs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02529 - Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24066 - PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16215 - ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01709 - When LLMs Sit Above Diagnostic Tools: Unrealized Complementarity in Industrial Fault Diagnosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05031 - How AI Writing Assistance Distorts Perceptions of AI Users and Their Opinions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.22503 - SOAR: Source-Aware Reinforcement Learning with Precise Credit Assignment for Search Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13157 - Towards Enriching Design-Time Models with Evidence from Simulation and Operational Activities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13456 - Smoothing the Top-k Exposure Boundary for Sparse Mixture-of-Experts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11575 - A Better Metric Will Not Save You: What You Compare Beats How You Compare It Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13476 - MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12757 - AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12545 - Measuring Artifact Reliance in Machine-Generated Text Detectors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13583 - Tracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query Expansion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13810 - Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13510 - The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.13154 - Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08003 - AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13627 - Multi-Stream Attention Residuals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13630 - Adaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV Hierarchy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13708 - Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12601 - 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 - Unreliable Narrator Framing as a Cost-effective Mechanism for Satire Explanation of Australian and American Satirical News Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12863 - MoPrO-SD: Modular Prompt Optimization for Stance Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13386 - Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue Resolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13563 - BoundaryEvo: Data-Model Co-Evolution at the Capability Boundary for Long-Chain Reasoning Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13285 - StreamDecisionBench: Evaluating Decisions in Force on Evolving Language Streams Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38612 - CLUE: A Contrastive Learning Framework for Unsupervised Event Type Induction and Annotation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12580 - KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13060 - The One-Word Census: Answer-Choice Conformity Across 105 Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12796 - Vision Transformers Learn Word Meaning from Images Alone Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13252 - S$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13202 - The syntax of wh-agreement in Yemeni Ibbi Arabic Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04986 - Structural Automata for Neural Semantic Parsing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13896 - Les Mis\'erables Dialogue: A film-based network representation of social communication Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13148 - Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06650 - What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12995 - Taking Tokenization off the Host for Agentic LLM Serving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13325 - CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual-Textual Alignment for QA-Style Radiology Report Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13059 - When History Helps and Hurts: Selective History Use across Multimodal Turns Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11948 - Time Delay System for Sequence Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12864 - Probabilistic Calibration Is a Trainable Capability in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11845 - Activating the Annotator: Operationalising Lived Experience in Data Annotation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12701 - BLiMPPI: Benchmark of Linguistic Minimal Pairs for Polarity Items Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13607 - Retractions Revisited: A Replication, Extension, and Mechanistic Evaluation of Linguistic Obfuscation Effects in Fraudulent Science Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13678 - A Privileged Teacher That Only Scores Cannot Search: Critique-Conditioned On-Policy Self-Distillation for Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13744 - Recurrent Harness for Agentic Continual Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12668 - ResidencyRL: Reinforcement Learning in Simulated Clinical Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07418 - Benchmarking Embedding Geometries and Clustering Algorithms for Unsupervised Patent Claim Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12997 - MVGraph: Benchmarking LVLMs on Evidence Composition across Multi-View Visual Graph Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12961 - Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13058 - Contextual Correction of Parallel Draftsfor Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12570 - Assessment of Generative Named Entity Recognition in the Era of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17898 - TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07767 - U4RASD at KnowledgeGraphEval-2026: Ontology-Constrained Encoder and LLM Systems for Arabic Relation Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12742 - Overcoming Data Imbalances with Expert Selection Biases Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13370 - EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37686 - InterviewPlayground: A Validated Simulation Environment for Evaluating AI Interviewers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12023 - Large Language Models, Machine-Assisted Cultural Analytics, and the Agentic Turn Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12792 - GeoFitBench-LLM: A Benchmark for Assessing Large Language Models' Capabilities in Geospatial Data Requirements Elicitation for Geo-Analytic Tasks Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.12669 - Let Large Language Models Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15419 - Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graph Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13695 - GeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13035 - Language Models Have Interpretable Narrative Mechanisms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12989 - Enhancing Legal Reasoning in Pre-trained Language Models via Knowledge Graph-Guided Multi-Task Pre-training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13722 - Cancerous Backdoor Attack: Gradual Activation via Invisible Tokens and A Stage Controller Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12644 - Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13128 - Host-Aware Web Crawling for LLM Pretraining Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13321 - Self-Preservation in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12602 - SharP: Soft and Hard Prompt-Guided Augmentation with LLM for Low Resource Fake News Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13207 - Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries Reveal Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.15738 - MS-GLA: Multi-Scale Gated Linear Attention for Addressing Representational Bottlenecks via Multi-Temporal Resolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35664 - What Do Audio-Language Judges of Generated Music Listen For? Four Probes with Controls from Expert Ratings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13247 - ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13395 - Error Rate is Not Enough: Costs of Augmentation in Low-Resource ASR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13807 - A Multi-Agent LLM System for Automated Tuning of Specialized Neural Network Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13663 - Personalization Without Stereotyping: Do Speech LLMs Know When to Turn a Deaf Ear? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13550 - OARelatedWork: A Large-Scale Dataset of Related Work Sections with Full-texts from Open Access Sources Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.01930 - perturber: A Stateless Service for Semantics-Preserving Text Perturbations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12667 - SEEDS: Preview-Guided Evidence Admission for Search Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12932 - Exploring Attention Sinks in Text-to-Image Transformers from Diffusion and Autoregressive Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13337 - OpenPA: Forced-alignment-free Multi-granular Pronunciation Assessment with Mixed-transcript Adaptation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13826 - REFLECT: Role-Aware Detection of Sentiment, Emotion, Politeness, and Formality Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13797 - Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22807 - Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38972 - Neurograf v1: An End-to-End Romanian-First Language Model Family Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13134 - Can Language Models Learn When to Abstain? Policy Learning and Calibrated Answer Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13821 - RAMP: Recurrent Adaptive Mixed Precision for Efficient Prefill in Recurrent-Depth Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13041 - Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09772 - zip2zip++: Towards Inference-Time Token Compression with Minimal Quality Loss Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13605 - Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09365 - VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12813 - Measuring and Mitigating Solution Mode Collapse in RLVR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11064 - Training User Simulators with Latent Intrinsic Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13617 - Kairos: Toward a Byte-Level Foundation Model for Every Modality Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12495 - One Model to Loop Them All: Elastic Latent Recurrence for Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12582 - Temporal Evidence Forests for Long-Horizon Multi-Party Conversational Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12874 - Rethinking the Roles of Diffusion and Decoding: Predictive-State Flows for Parallel Language Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12898 - S-Space: Exploring Spatial Workspace in Multimodal Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13527 - Encoder Awakening via Adapters: Effective Domain-Adaptive Fine-tuning of Speech-LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17981 - EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13021 - OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38345 - Forecasting Corpus-Sampling Disagreement in Masked Text Reconstruction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12987 - Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11542 - SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12596 - REDaCT: Collapse-Free Unlearning in Large Reasoning Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12769 - EchoDistill: Robust Large Audio Language Models via Noisy-to-Clean Self-Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23954 - Unsupervised Multimodal Reward Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12707 - GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12617 - Quantum Vision Theory Applied to Audio Classification for Deepfake Speech Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08104 - Towards the Roof of the World: NLP Progress in Tibetan Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13398 - Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13277 - Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13840 - From Structure to Validity: Mechanism-Guided Generation and Refinement of LLM Rubrics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13375 - Meta-Reflective Evolution Effectively Improves Production AI Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12794 - Agreement Without Alignment: Label-Free Rubric Clarification Increases LLM-Judge Consensus but Not Agreement with Humans Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13303 - CoBe: A Benchmark For Conversational Counterfactual Text Editing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13057 - An Input-Dependent Readout Phase for Resonant Sequence Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12496 - TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28640 - Weight Clustering Reveals the Importance of Relative Rank in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17917 - Proactive Agentic Orchestration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13485 - Bolzano: From Expert-Guided Proof Search to Automated Open-Problem Solving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09769 - Epistemic Policy Divergence in Multi-Turn LLM Contamination: A Protocol-Gradient Investigation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35308 - Medical foundation models converge less under label supervision Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20274 - ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.10998 - Dialects of Translationese Shape Language Model Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16469 - COBALT: Contextual Bandit Learning with Offline Trajectories for Multi-Turn Code Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03806 - SmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12975 - Knowing Is Not Telling: Identity Ossification in LLM Representations of Trans-border Communities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12610 - SWE-Duel: Towards a Self-Scaling Arena for Coding Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12569 - QTestBench: A Test Framework for Evaluating LLM-Generated Quantum Code Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13811 - Self-Aware Knowledge Probing: Evaluating Language Models' Relational Knowledge through Confidence Calibration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.18901 - RSI-Anything: Unlocking Recursive Self-Improvement with World Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13912 - People Making Conversation: Evaluating How Naturally Speech Models Converse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12802 - ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.17244 - DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05615 - Fear Is Not Always Fear: Variation in Emotion Label Equivalence Across Datasets Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12841 - Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13672 - MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10268 - UkrMeme: Multimodal Explainable Persuasion Detection in Ukrainian Memes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13783 - Generating Edit-Inducing Questions for AI Research Manuscripts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36617 - ZenGen: Social Mind for LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23740 - PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10455 - JANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13194 - OccludeBench: Can VLMs Find What's Missing? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13790 - APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13623 - When Charts Deceive Web Agents: A Paired Benchmark for Misleading Visualization-Grounded Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12823 - COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12837 - Agents' Last Exam Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05405 - Reasoning-Token Spikes Under Prompted Untruthful Responses in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10405 - Do Prompt Optimizers Break Requirements They Are Not Scored On? A Preregistered Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13287 - Not Just an Evaluation: A Case Study of Discourse Particle Sensitivity in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13794 - Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13432 - Task Context Shapes Component Roles in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13895 - Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.22184 - Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17633 - Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12133 - M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.29125 - DistressBench: Evaluating Multi-Dimensional Crisis Support in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12758 - When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical Priors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13910 - Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12939 - EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03678 - AgroGround: Multi-Granularity Grounded Recognition in Agriculture Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04425 - Cognition-Oriented Emotion Tracing from Causes to Consequences in Real-World Social Scenes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11410 - Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12933 - RESCUE: Is This Alarm Worth Acting On? Counterfactual Evaluation of VLA Runtime Monitors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13516 - Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13078 - DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13767 - LeWAM: End-to-End World and Action Modeling with JEPAs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12818 - Enhancing Tabular Learners with Context-Aware Semantic Embeddings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03565 - Scaling Agentic Data for Long-Horizon Terminal Intelligence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13166 - Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00726 - Can escalation channels redirect reward hacking toward defect disclosure? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29460 - DeFiRank: Federated Pairwise Ranking for Governance in Decentralized Financial Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12916 - Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13521 - When MLLMs miss what humans read: diagnosing and learning to read squint text Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13465 - Work While They Sleep: Exploiting Evaluation Latency for Fully Bayesian Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08969 - Claim-Gated Source-Risk Auditing for Generative Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29145 - Not All Dimensions Are Equal: Outlier-Aware Attention Linearization with Grouped Quadratic Kernels Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13674 - GOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03861 - Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13330 - Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00661 - MultiWorldBench: Do Independently Controlled Views Describe One Shared World? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11723 - A Baseline Assessment for the Agentic Web Technology Stack Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13703 - Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13536 - Provably Accurate Shapley Value Estimation via Leverage Score Sampling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.01917 - SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13081 - Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11374 - Collaborative Learning and Reasoning over Model Slices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12927 - Scalable Circuit Learning for Interpreting Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16939 - When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13765 - From Mastery Profile to Simulated Response: Stochastic Student Knowledge Graphs (SSKG) for Faithful LLM Student Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21668 - Beyond Actions: Learning Future Operation Targets for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13212 - Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13438 - Efficient Audio-Visual Speech Enhancement via Reinforcement Learning-Based Neural Architecture Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12796 - SqueezeBench: Saturation-Resilient Evaluation of Mathematical Capability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13461 - Data-Driven Persona-Conditioned Agents for A/B Test Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01038 - Causal Effect Identifiability in Causal Abstractions: A Strict Hierarchy of Criteria Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13520 - Scaling Empowered Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13002 - Does Learning Recurrent Networks Matter in Partially Observable RL? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13197 - Sera: Semantic Representation Aggregation for Reliable and Interpretable Battery Health Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11567 - Learning to Report Unsafe Tasks in a Multi-Agent Game Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09002 - AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07900 - LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13075 - VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28422 - A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring) Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.22809 - Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12855 - Trajectory Prediction for Autonomous Driving in Road Construction Zones Using Human-in-the-Loop Driving Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12747 - Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.02817 - Machine Learning and Time-Series Foundation Models for Day-Ahead Electricity Forecasting in a University Building Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12638 - Green-Routed Neural Operators: Physics Determines Where the Network Reads Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05337 - Global Consistency Repair for Natural-Language Claim Sets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13600 - Video2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04432 - Beyond Semantic IDs: Finite-Beam Reachability and Continuous-Query Generation in Generative Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12977 - CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09159 - Preference Elicitation for Policy Optimization and Application to Aligning Heart Transplantation with Human Values Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28620 - DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30386 - TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07043 - SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13356 - AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.07427 - FactoryNet: A Large-Scale Dataset toward Industrial Time-Series Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09081 - When Generative Models Act as Simulators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12847 - Does Location Matter? A Black-Box Causal Audit Reveals Model-Dependent Audio Grounding in LALM Hallucination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13112 - Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13022 - Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12593 - RegulaTutor: A Theory-Informed Framework for Long-Term Personalized Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13399 - Conversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10434 - DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13116 - AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13184 - Web$hell: A Unified Interface for Agentic Web Access Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13416 - Heterogeneity-Aware Client Sampling for Optimal and Efficient Federated Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.11304 - Preference-Conditioned Multi-Objective Reinforcement Learning for Tactical Decision Making in Heavy-Duty Vehicles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.18783 - Learning Size Independent Constraint Models from Input Data and Positive and Negative Example Solutions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13640 - MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13829 - Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.11849 - Scale and Selection: What Makes Automatic Harness Evolution Work for Visual-Interface Robot Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39304 - Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12598 - Branching On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13481 - The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-Assisted Software Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27045 - Access Paths for Efficient Ordering with Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.00303 - MPMMine: Better Benchmarks for Constraint Acquisition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26279 - FACT: Fidelity-Aware Construction of Articulated Twins Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37067 - Faithful and Complete LLM-Assisted Automated Construction of Hierarchical Hardware Knowledge Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12762 - When Should the Teacher Move? Temporal Coupling and Stability in Self On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03532 - Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13660 - When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11928 - HAFixAgent: History-Aware Agentic Program Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.01047 - Same Query, Different Answer: Run-to-Run Variance in Semantic Query Processing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13823 - Towards Defining, Measuring, and Leveraging Creativity in AI Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12845 - Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21282 - Representation Alignment from a Few Paired Data via Distilled Optimal Transport Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12781 - MAGMA-Bench: Evaluating Long-Horizon Embodied Agents under Dynamic Tasks and Execution Failures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13534 - VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13145 - One-Step Text Generation by Seq-Drifting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12879 - Localized Generative Design of Ship Hulls with Diffusion Models and High-Fidelity Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12870 - From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06411 - LAPT-Scale: Scaling Embodied Policies with Latent Action Pre-Training on Human Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13732 - MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10064 - Semantic Views: Certified Reuse of LLM Labels Across Semantic Queries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12768 - Looking Ahead and Back: Anticipatory Generative Modeling for Road-Network Trajectories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13131 - CASCADE: An Agentic Regulatory Network Framework for Patient-Data-Validated Downstream Perturbation Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05359 - Constructing Pareto Frontiers of Optimal Reasoning Termination Methods for Overthinking in Reasoning Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13570 - Evolving Hybrid Quantum-Classical Architectures for Image Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03220 - AI-Based On-Board Maritime Object Detection for Earth Observation Payload Data Reduction on Versal Embedded Hardware Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12182 - Matched-Context Group Policy Optimization for LLM Agent Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13755 - Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13735 - IBBench-Light: A Paired Evaluation of Task-Conditioned Responses to External Directives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13725 - Teaching neural decoders with language Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12921 - NeuronSpark: Selective Spiking State Space Models with Adaptive Computation for Language Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16148 - Model-agnostic Knowledge Augmented Machine Learning for Weakly Annotated Bioimaging Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13637 - Discovering Phase Space Structure in Learned Hamiltonian Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.23003 - AgentSWE: Can Coding Agents Build the Agent You Actually Want? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13361 - Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13909 - MyoSem: Aligning Electromyography with Natural-Language Action Semantics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00174 - Competence-Aware Orchestration for LLM-Based Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13144 - STAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09524 - Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09109 - SUN: Reaching for Novelty in Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08642 - H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01216 - LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10722 - Hierarchical Experimentalist Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29315 - SpatialASM: Internalizing Active Mentalization for Spatial Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13832 - Hindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task Characteristics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13000 - Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13494 - MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12659 - EliteTable: Self-Improving Program Search for Executable Control Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12536 - MIRROR: Learning from the Other View for Multi-Modal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21552 - What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations) Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06202 - Higher-Order Action Supervision Makes A Strong Policy Class Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11175 - Agentic Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13455 - PRIME: Pre-Retrieval Index Modeling Enhancement for Structured Document Retrieval-Real Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.13296 - Who&When Pro: Can LLMs Really Attribute Failures in AI Agents? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09996 - The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04296 - Graph World Models for Constrained Epidemic Policy Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35545 - CircuitTree: Composing Circuits into A Syllable Transcriber Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12520 - From SGD to Muon: Adaptive Optimization via Schatten-p Norms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19781 - Decoupling the Declarative from the Procedural in Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21496 - RoboMME-Interference: Benchmarking Robot Memory Under Interference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22338 - Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13632 - Mixture-Greedy for Online Generative Model Selection: Is UCB Necessary in Diversity-Aware Multi-Armed Bandits? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21716 - Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12822 - Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12881 - TDDN: Text-aligned Diffused DINO Network for Puzzle Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07937 - SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13626 - UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09040 - API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08861 - Kronecker Product Attention: Memory-Efficient KV Compression via Structured Factorization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12657 - A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13479 - Do More Agents Help? Evaluating Accuracy and Cost in LLM Multi-Agent Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05670 - Your Discrete Graph Diffusion Model is Secretly Memorizing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13786 - GraphDecisionBench: Benchmarking System One Models on Graph Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06354 - SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08149 - OTel: Open Telco AI Datasets, Benchmarks, and Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07766 - VETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13098 - LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.09956 - UniConFlow: A Unified Constrained Flow-Matching Framework for Certified Motion Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.02955 - Calibration in One Go: Jointly Learning Accurate and Calibrated Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13693 - Local Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHC Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13437 - A Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPO Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13669 - Energy-Efficient Spiking Neural Networks for Sensing-Aided Beam Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12507 - MathVis: Can AI Reason through Drawing? A Benchmark for Mathematical Figure Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12954 - DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18048 - LensVLM: Selective Context Expansion for Compressed Visual Representation of Text Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07019 - CLEAT: Learning Value-Guided Clarification for Interactive Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12655 - The Convention Gap: Beyond Literal Content in Human-AI Cooperation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.11489 - IAD-Unify: Task-Specific Interfaces for Industrial Anomaly Understanding, Segmentation, and Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12440 - Physics-guided surrogate learning enables zero-shot control of turbulent wings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09434 - ITO: Multi-View Alignment and Training-Time Fusion for Image-Text Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02767 - FactoryBench: Evaluating Industrial Machine Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07675 - Improving Certified Robustness via Adversarial Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31653 - ThinkNet: Evolutionary Deep Ensembles for Efficient Motor-Imagery EEG Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33967 - Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13015 - Useful to Whom? The Easy-versus-Coverage Boundary Moves with the Learner Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00221 - First-Order In-Context Shapley: Scalable Data Auditing for LLM Alignment and Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22766 - Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13504 - MENTOR: Learning from Failure with On-Policy Pedagogical Intervention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13594 - From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.19364 - CNN-Transformer with Sigmoid Label for High-Resolution Sub-Degree DOA Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13433 - Fast LapSum: Exact Differentiable Top-$k$ at Million Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06912 - Towards a Measure Theory of Semantic Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.00525 - Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23811 - ReSFlow: Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13225 - EvoBelief: Falsifiable World Models for Self-Improving LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12789 - JEV-as-a-Judge: Accept When Confident, Escalate When Unsure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26550 - Trust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on Authored Security-Regression Proxies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19844 - What Makes Adversarial Examples Transfer Across Deepfake Detectors? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10002 - The Evidence Anchoring Boundary: Where Visual Interventions Matter and When They Help in Multimodal LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12981 - WoundAmbit: Bridging State-of-the-Art Semantic Segmentation and Real-World Wound Care Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.06185 - Sampling-Based Safe Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19469 - Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12984 - Evolving Creatives with Clicks: CTR-Driven Advertising image Editing via Attribute Disentanglement and Preference Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13066 - Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13267 - Quality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-Tuning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13152 - CORE-Seg: Reasoning-Driven Segmentation for Complex Lesions via Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.05911 - Solving VeriContest with a Lean-Backed Rust Verifier Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03994 - KITE: A Knowledge-Injected Temporal Encoder for Time-Series Event Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12738 - Can Language Models Play the Wikipedia Game? Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.13948 - SelectArena: A Modern Benchmark for Feature Selection on Real-world Tabular Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13644 - Automatic-Differentiation-Enabled Finite Element Model Updating: Learning Constitutive Neural Networks from Structural Deformation Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05199 - Collaborative Theory of Mind: Learning to Self-Revise by Anticipating User Responses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12872 - Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07251 - Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03753 - Co-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull Requests Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12849 - Tabular Foundation Models Are Effectively Shallow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13253 - Understanding Transformer-based Vision Models through Inversion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.06534 - Mesh-Native Tokenisation: Retrofitting Foundation Models to Unstructured Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12618 - Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04528 - SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13737 - Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01487 - TypedBench: A Benchmark for Calibration, Framing Sensitivity, and Cost in System One Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11392 - Continually Post-training Small Models via Synthetic Self-distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13113 - Neural networks are more modular than single neurons suggest Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12842 - ReplaySSM: Cache SSM Inputs, Not State Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13778 - OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.12914 - Hide and Seek: HIDE Concepts to SEEK explanations for black box models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13935 - Learning from All-Failed Groups via First-Visit Coverage in Long-Horizon Agentic Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22724 - Robustness of Reinforcement Learning-Based Congestion Management in Low-Voltage Grids Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.16004 - JoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.12957 - FORTE: A Production Framework for Feature Evaluation and Deprecation in Industrial Recommender Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13806 - AlphaNIST: Emergent Assembly Skills from Binary Task Rewards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13354 - AI-Mediation in Retail Markets: Revenue Effects and Assortment Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12917 - GenCoord: Executable Commitments for Embodied LLM Agents under Private Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22055 - DP-MIND: Differentially private memory-guided Long context Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13132 - Convex Optimization of Spiking Neural Networks with Global and Approximation Guarantees Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08022 - Erased, but Not Gone: Output Forgetting Is Not True Forgetting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25001 - In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13411 - TelcoAgent: A Scalable 5G Multi-KPM Forecasting With 3GPP-Grounded Explainability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19821 - RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13172 - When Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13092 - DeltaLLM: Delta-Key Sparse Attention for Edge LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.19608 - Equal-Budget Monte Carlo Tree Search versus Randomized-Restart List Scheduling for DAG Workflows: A Controlled Equal-Budget Computational Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12542 - Protocol effects on feature-based hardware-Trojan detection across Trust-Hub families Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07199 - Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02626 - Incremental Retrieval-Augmented Generation for Human-in-the-Loop Decision Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12666 - Collective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human Drivers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13439 - The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05328 - On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02095 - Agent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13273 - X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13886 - AudioTETRIS: Token Elimination via Transitional Importance Signals for Efficient Audio LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13600 - Provenance-Aware Belief Updating in Human-AI Feedback Loops Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13008 - MotionCoach: Constructing Multimodal Guidance for Video Professional Motion Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12963 - Physics-inspired Generative AI models via real hardware-based noisy quantum diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.22193 - Estimating Great Expectations Under Autoregressive Language Models with Potentials Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11399 - RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13889 - Agent Step Value: Auditing Evaluation-Channel Sensitivity in Black-Box Agent Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04419 - Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04518 - CRM: Retrieval Model with Controllable Condition Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2412.13844 - Hyper Algorithm Design Agent: Evolving Learnable Optimizer from Zero Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35328 - Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12493 - Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01892 - RLVR$^{2}$: Reinforcement Learning with Verifiable Rubric-based Ranking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23457 - Amortized Counterfactual Prediction with Graph Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13724 - Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08037 - Variance-Reduced Policy Gradient is Nearly Minimax-Optimal Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13692 - Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19386