TILens Daily Edition 2026-10-31 Filters: topic=ai, github=hidden Stats: 525 articles, 11 sources, 503 research papers Top topics: AI, AI Research, General ## News - Create an AI Voice Agent for Customer Support Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/voice_developer/create-an-ai-voice-agent-for-customer-support-a2f - OpenAI reportedly lowers funding target for new round Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/31/openai-reportedly-lowers-funding-target-for-new-round/ - AI Agent Security Guardrails: Tool Permissions and Human-in-the-Loop Controls Source: java-code-geeks Topic: Java (+AI) URL: https://www.javacodegeeks.com/ai-agent-security-guardrails-tool-permissions-and-human-in-the-loop-controls.html - OpenAI Halves the Price of Its New Everyday AI Model Source: real-python Topic: Python (+AI) URL: https://realpython.com/ai-news-weekly-2026-10-30/ - GPT-6.1 Terra vs. Claude Opus 5.5: Cheaper and faster in three tests at max effort Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/gpt-6-1-terra-vs-claude-opus-5-5/ - A public ChatGPT share could run code as you. I checked the two parts that made it possible. Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/frankchu/a-public-chatgpt-share-could-run-code-as-you-i-checked-the-two-parts-that-made-it-possible-2gji - The Neuron Academy - Dedicated Send - 10.31.26 Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/the-neuron-academy-dedicated-send-10-31-26/ ## Research - How to Build Bug-Free Applications with Claude Code Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-build-bug-free-applications-with-claude-code/ - We Taught AI to Answer Questions. Who Taught It to Change Its Mind? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/we-taught-ai-to-answer-questions-who-taught-it-to-change-its-mind/ - I Told an AI Agent That Its Wrong Answers Were Right. One Model Believed Me. Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/i-told-an-ai-agent-that-its-wrong-answers-were-right-one-model-believed-me/ - "Close enough?" An investigation into multiplication errors in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38634 - Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37708 - One Confidence Threshold, Unequal Coverage: Language Gaps in Typed Decision Interfaces and How Translating Inputs Reduces Them Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37688 - Scan Before You Install: Detecting and Mitigating Local and Composite Vulnerabilities in Skills Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37901 - Locating and Closing Information Gaps in Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40186 - Understanding axial attention in TSFMs through single location regression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40188 - Verifiable LLM-Guided Focal SMT Solving for Quantified Arrays Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39435 - ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02004 - DeFT-RAG: Incrementally Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37826 - TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40276 - Artifact Distillation: Training-Free Transfer from Frontier to Small Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37680 - Benchmarking Graph Neural Networks for AC Power Flow: The Role of Inductive Biases and Physical Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38985 - SaiVLA-JEPA: Evaluating Future Latent Prediction in JEPA-Conditioned VLA Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38508 - WebAnything: From the Wild Web to Scalable Agent Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37786 - Raincheck: Deferred Multimodal Prefill for Efficient Multi-Turn MLLM Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39562 - From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38532 - Practical Assessment of Agentic Systems in Acoustics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39685 - When Is Smaller Greener? Right-Sizing Language Models for Agentic AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19345 - Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38755 - Rank-Aware Differentially Private Release of Listwise Preferences for LLM Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37682 - From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39114 - CuraEval: Evaluating Demonstration Curation on Mixed-Skill Robot Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38221 - Measuring Deep Learning Performance - An Empirical Study of Performance Distributions Across Architectures and Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38037 - A Case Study of a Multi-Agent Kernel-Optimization Loop That Learns a New AI Accelerator Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38329 - What Does "Now" Mean to Your Computer-Use Agent? Stale Screenshots, Page Loads, and Which Check to Run Before a Click Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39282 - MetaRefine: Score Refinement with Multi-Level Features for Image Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40487 - Poisoned Skills: Propagating Jailbreaks Through Agent Markdown Files Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37738 - Predict the Reward, Not the World: World Reward Models for ML Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38439 - Efficient Scalable Oversight via Rewinding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40535 - Certified Access: Test-Time Compute on Conservative Physics-Structured AI Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39073 - EventSeeColor: Learning to Reconstruct Color from Monochrome Events Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40166 - Invert4TVG: A Temporal Video Grounding Framework with Inversion Tasks Preserving Action Understanding Ability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.07388 - The Anatomy of Socio-Demographics in Pluralistic Offensiveness Modeling: When and Where It Helps, and the Role of Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37896 - The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.21380 - Timbre: Reliability-aware harmonic consensus for label-free multimodal test-time rexinforcement learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39439 - Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38342 - Multi-output LSTM soft sensors for industrial anaerobic co-digestion using LSTM-beta-VAE generative data augmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39768 - ATLAS-Bench: An Agentic Tool-Use Benchmark for Local Area Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39438 - Inner-Learning: From Hand-Coded Beliefs to Declarative Knowledge in Trick-Taking Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38304 - Manifest-Assisted Retrieval in Artificial Intelligence Search: Evidence Gaps and a Security Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38361 - Agentic process evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40071 - Decision and System One models in rheumatology: accuracy and calibration on specialty-training examination questions and diagnostic case vignettes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40318 - Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.00361 - Dual-Evolving Reinforcement Learning for Automated Reward Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13399 - Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38411 - Lev-3B: A Data Recipe for Compact Probabilistic Log Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38915 - HERA: Assessing an Autonomous Agent for Quantum Device Measurement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39074 - Seq@K: Evaluating Language Models Under Sequential Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37859 - Aligning Medical Vision Language Models at the Capability Boundary with Entropy Adaptive Rubric Grounding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39835 - Training language models in simulation for psychiatric intake Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40476 - RetroChessBench: A Benchmark for Reconstructing and Proving Chess Histories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39341 - The Indian Financial Automated Advice Bias (IFAAB) Dataset : Auditing Socioeconomic and Demographic Disparities in LLM-Generated Financial Advice in India Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38239 - Merge and Branch: Efficient Tree-Structured Supervised Fine-Tuning of LLMs for Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37973 - MUSE: Multi-Level Memory with Selective Runtime Injection for Scientific Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38332 - Forget Attention: Importance-Aware Attention Is All You Need Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02332 - Retaining Repair Hypotheses for Cost-Aware Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39410 - Right Numbers, Wrong Questions: Evaluating LLMs on Underspecified Financial Queries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38631 - Implicit Reasoning in Transformers: Bridging the Compositionality Gap in GPT-2-like Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39016 - From Geometry to Behavior: How Instruction Exposure Unlocks Latent Rhetorical Directions in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37685 - Amortized Localized Posterior Inference for Model Calibration with Application to an Ocean Turbulence Closure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37731 - A Unified Hessian-Guided Framework for Post-Training Quantization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40345 - Sparse Fine-Tuning for Parameter-Efficient Adversarial Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39455 - Jailbreak Connectivity: Towards Diverse, Transferable, and Universal Multimodal Large Language Model Jailbreak Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38091 - What Should a Navigator Remember? Spatiotemporal Memory for Zero-Shot Vision-Language Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38318 - Understanding and Mitigating Role Spoofing in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40396 - Compile Away Uncertainty: Self-Evolving Agent Skills via Programmatic Compilation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39508 - UMI-Live for In-The-Wild Bimanual Robotics Data Collection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39385 - ASIWorld: Benchmarking Autonomous Agents in a Persistent Survival Sandbox Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14807 - Precedent or Intent? What Coding Agents Follow When Evolving Existing Code Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38244 - An Introduction to Large Language Models for Scientists and Professionals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37684 - Encounter-Driven City-Scale Human Mobility Generation with Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17672 - The Coordination Tax and the Heterogeneity Dividend: Break-Even Conditions for Multi-Agent LLM Pipelines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37700 - CauProphet: Teaching Agents to Develop Causal Cognition like Humans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32477 - From Natural Language to Real Schematics: An Automated Workflow for Power Electronics Schematic Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38201 - When AI performs, what remains? An integrative review of generative AI and cognitive capital in individuals and organizations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38647 - Vendster: An Evaluation Arena to Investigate How Forecasting Tool Quality Affects LLM Agent Behaviors in Buyer-Vendor Negotiation Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.38292 - Learning Safe Flow Matching Robot Policies from Binary Feasibility Oracles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40075 - Calculation and rejection diverge in language models tested at known mechanical limits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38096 - The Role of Quantization in Loss Spikes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38277 - AgentDecept: Benchmarking Deceptive Behavior in Tool-Using LLM Agents under Pressure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39377 - AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00425 - When the Same Prompt Gives Different Answers (and the Same Answer Isn't Always Right): A Taxonomy of Failure Mechanisms, Testing, and Mitigation Strategies for LLM-Assisted Evidence Synthesis Read-and-Evaluate Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39070 - Prototype-Guided Dynamic Domain Modulation and a Large-Scale Multi-SKU Benchmark for Shampoo Bottle Surface Defect Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38194 - Search-Guided Reasoning Trace Curation for Verilog Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37706 - Selective Transfer Learning for Groundwater Level Anomaly Forecasting: Accuracy-Risk Trade-offs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37733 - Telling Is Not Seeing: Textual Personas Rarely Make Vision-Language Models Answer Like the People They Describe Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39331 - PairCLIP-SWA: Similarity-Guided Balancing and Stochastic Weight Averaging for Generalized Deepfake Image Detection with OpenCLIP Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37874 - A general extractor for coherent patterns across time-frequency measurements Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.20317 - CoToan: Executable Rules and a Representation Contract for Reproducible Game AI Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39353 - The System Hallucination Scale (SHS): A Human-Centered Instrument for Assessing Perceived Reliability of Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09989 - From Profiles to Steering Vectors: Global Sparse Priors and Local Semantic Calibration for Personalized Text Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21620 - CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38573 - inkGround: Benchmarking Fine-grained Visual Grounding Capabilities of Vision-Language Models for Cursive Handwriting in the Wild Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38720 - Agentic AI for Clustering and Relationship Discovery in Prediction Markets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.02436 - Sandman: Building and Operating Sandboxes for Agentic Reinforcement Learning on Shared Kubernetes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39711 - TableTune: Measured, Self-Correcting Draft-Length Tables for Dynamic Speculative Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38968 - Latent Style-based Quantum Wasserstein GAN for Drug Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.22399 - NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.11234 - Algorithmic Bias from the Perspectives of Healthcare Professionals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38006 - Verification Learning Theory: A Process Model of Checking and Retention in AI-Assisted Judgment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37875 - FilingLoop: Evaluating and Evolving LLM Agents for Corporate Disclosure Review and Revision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37905 - Accumulating Pruning Constraints: New Exact Polynomial-Space Algorithms for Max 2-SAT Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39992 - Self-training for cross-centre coronary vessel segmentation in X-ray angiography using pre-contrast frame subtraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40302 - Towards Training Transformers as a Universal Computer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25166 - Interpretable Feature Discovery from Unstructured Data Using LLMs and Statistical Choice Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38082 - When Should AI Decide, Defer, and Deviate? Responsible Automation for Deceased Donor Kidney Allocation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39045 - Semantic Mismapping in Generalized Category Discovery: Evaluation and Mitigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39356 - An Alignment Benchmark for Enterprise Agents on Era by Eon Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38544 - InferD: A Honeypot Framework for AI Inference Infrastructure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39807 - Noise Steering: Exploiting Wake Steering and Acoustic Directivity for Noise-Constrained Wind Farm Control via Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36888 - CopyLoop: Fast Looped Transformer Decoding via Context Copying and Shallow Screening Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38822 - Hammering with Vampire in Lean Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40310 - Incorporating Machine-Others: An Enactive Exploration of Human-LLM Interactions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39869 - Red-Teaming Large Language Models in Low-Resource African Languages: A Case Study of Yoruba and Nigerian Pidgin Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39590 - Mitigating the Likelihood Paradox in Flow-based OOD Detection: An Entropic Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09581 - VeriCUA: Verification as Agentic Exploration for Computer-Using Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40578 - Agentic University: Collaborative Agents for Personalized Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40492 - Prompts and probabilities in the linguistic assessment of language models: Evidence from semantic focus-sensitivity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39923 - Kairos: Semantics-Aware Orchestration of Planning Engines across Classical, Numeric, Temporal and Hybrid PDDL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39454 - Advancing Clinical Genomic Analysis with a Skill-Centred Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40556 - UPPAAi: Towards LLM-Assisted Modeling, Verification, Analysis and Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40042 - Statutory Article Retrieval from Arabic Judicial Narratives: Family Law and Law of Evidence in Saudi Arabia Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.38336 - The Athlete as a Scientist of One: Agentic Bayesian Experimental Design for Individualized Physiology from Consumer Wearables Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40370 - When Skills Tell Agents Not to Ask: A Large-Scale Study of Oversight Directives in Agent Skills Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37734 - Ramanujan Challenge Results: AI-Assisted Evaluation Pipeline for Multi-Format Proofs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40551 - SciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37919 - Anagent For Enhancing Scientific Table & Figure Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10081 - Evaluating Causal Reasoning in LLMs: A Case Study in the Challenges of Procedural Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38100 - PepEVOLVE: Position-Aware Dynamic Peptide Optimization via Group-Relative Advantage Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.16912 - Rethinking Pre-pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40051 - Rocks, Pebbles and Sand: Modality-aware Scheduling for Multimodal Large Language Model Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26498 - SAFE: An LLM-as-Verifier Framework for Evidence-Grounded Multi-Hop Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01993 - Exact Algorithms for Multiagent Path Finding with Communication Constraints on Tree-Like Structures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.08556 - The Importance of Speech Genre for End-of-Turn Detector Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39742 - LLM-Assisted Optimization for Simulation-Based Redesign Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.39275 - Evaluating and improving AI agents for sequencing protocol understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37851 - HEMO: Harness Self-Evolution for Multi-Objective Combinatorial Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40023 - Letting AI Formulate the Research Question: Autonomous Research Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39620 - Echo: Scaling Visual Reinforcement Learning with Off-policy Experience Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37865 - Disparity Laundering: Consensus Without Fairness in Clinical Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38215 - Pre-Crime for Agents, at the Last Second: Probing When a Recruited Agent Gives In Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40588 - Cheap Retrieval and Observation Credit Assignment from One Quantity: The Value of Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40030 - From Error Prediction to Causal Influence: Auditing SAE Features in Multiple-Choice QA Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38067 - Can Event Detectors Leave the Broadcast Camera? Evidence from Tennis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38042 - DES-JEPA: Learning a Shared Vocabulary for High-Dimensional Discrete Event Sequences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38445 - Well-Specified and Well-Tested? Assessing SWE-bench-Style Datasets with a Self-Evolving Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39417 - What Does an Ontology Catch? Curated, LLM-Generated and Data-Derived Ontologies as Checkers of LLM Agents over Knowledge Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37809 - The Control Layer Behind Rule-Following Agents Trading Across Market Conditions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26324 - Where Position Matters: Profiling-Guided Layer-Wise RoPE Allocation in Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39223 - Co-Evolving Policy and Rubric via Capability Awareness for Open-Ended Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38566 - PRISM: Festina Lente Proactivity -- Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01532 - Intrinsic Distribution Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39633 - A Negotiation-Aware Hybrid LLM Framework for Intent Interpretation and Service Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40161 - Bouba Beats Kiki, and Other Regularities in the Subjective Preferences of LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37692 - From the Gettier Machine to Justified True Output: A Three-Step Account of Rational Trust in Generative AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38112 - The Real Cost of Context: Predicting Compute Time and Energy Consumption in LLM Prefill and Decode Phases Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39621 - Efficient Learning of Mechanism Designs and Compositionality Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40005 - Algebraic World Model: From Exploration to Proofs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40503 - AtomSteer: Test-Time Constraint Steering for Atomistic Generative Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38517 - A Tutorial on Generative Models for Music Audio Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38252 - On-Policy Self-Distillation with Teacher Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38637 - Process-Constituted Intelligence: A Shared Criterion for Humans and Machines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16213 - SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36991 - SCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38391 - Episodic looking - using reinforcement learning to bias perception enhances few-shot and continual learning with protection from forgetting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38577 - Beauty Is Human: When People Love AI-Generated Art, They Think a Human Made It Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38113 - Spectral Invariant Fusion and Refinement for Domain Generalized Semantic Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39926 - SatOps-Decision: Low-Latency Discriminative Decisions for Onboard Satellite Communication Operations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38697 - RePolicy: Learning to Select and Apply Safety Policies for Agent Safeguards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24275 - MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38946 - Probing Spatial State Representations in Visual Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40636 - DecisionUnlearn-Bench: Unlearning Probabilistic Decisions under Changing Schemas Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38431 - SparseTokenGS: Gaussian-based Sparse-View CBCT Reconstruction via Reusable Token Pool Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38360 - Efficient Agentic Audio-Visual Question Answering through Toolset Pruning and Modality Consolidation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38960 - WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07267 - Turbo4DGen: Ultra-Fast Acceleration for 4D Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.29572 - When to spend privacy: optimal allocation in private learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39954 - Can LLMs Faithfully Solve Ontology Engineering Tasks? A Mechanistic Interpretability Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38326 - Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38095 - Syntactic Segmentation and Collage Generation for Videogame Levels with Perceptual Distance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38987 - From Grind to Grasp Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38728 - Agent-Wise Test-Time Normalization for Camera-Based Cooperative Perception with Corrupted Collaborators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39505 - Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40647 - CovFedAvg: Local Low-Loss Curves and Federated Model Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39902 - How Deterministic SAST and AI Security Agents Divide the Work: Coverage, Harness Policy and Cost in Snyk VulnBench 2.0 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38617 - Detecting Covert Collusion between AI Agents through Partner-Outsider Positive Listening Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37849 - Tactus: Tactile & Pose Sensing Glove for Natural Dexterity Data Collection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39076 - Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40444 - Rethinking Bayesian Optimization for Co-Optimizing LLM Training Configurations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08351 - LLM-Driven, Datasheet-Aware Automated Hardware Compatibility Verification for Early-Stage, Pre-Schematic Embedded System Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25217 - Too Hard, Too Easy, Just Right: Performance-Driven Challenge Adaptation in Virtual Reality Firefighter Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38117 - DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.20709 - Enhanced image forensics through partial C2PA-based provenance information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38639 - Fast and accurate neural triage decoding of ultra-high-rate quantum LDPC codes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40490 - Learning Calibrated Confidence for Multi-Agent Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39927 - Safe Multi-Objective Reinforcement Learning: Zero Constraint Violation and Primal-Averaging Convergence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39409 - Rethinking GFlowNet Training: Negative Reinforce Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38994 - Learning Mental Models From Unreliable Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24528 - The Prestige: Benchmarking Cognitive Visual Reasoning using Magic Tricks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38103 - Are Seismic Foundation Models More Than Glorified Feature Extractors? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38003 - An Incremental Knowledge-Graph Learner Digital Twin for Evidence-Grounded Early Warning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36820 - PT$^3$: Prototype-Guided Self-Supervised Pretraining for Generalizable mmWave Human Point Cloud Representation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38551 - Evaluation Metrics for Safe Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15315 - Encode Once, Answer Many: Internalizing Context via Parametric Flow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38356 - Network Topology Does Not Matter: The Breakdown of Classical Consensus in LLM Populations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37699 - FIRME: Registry-Anchored Memory Graphs for Evolving, Heterogeneous Investor Knowledge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40482 - Joint Detection of Fraud and Concept Drift inOnline Conversations with LLM-Assisted Judgment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.07852 - Assessing Language Models for Scientific Applications: Inertial Confinement Fusion as a Use Case Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38024 - The Price of Failure Risk: Clipped Barrier Policy Gradients with Convex Regularization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.19193 - Turing LLM Post-Training: Calibrated Distillation and Efficient Dynamic-MoE Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39876 - Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39532 - Clean Sheets and Checkpoints: Evidence Complexity for Certifying Sequential Agent Risk Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39124 - MemSteer: Turning User Histories into Supervision for Agent Memory Optimization Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.39276 - Luggage re-identification: A study of strategies towards a real-world application Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40643 - FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39423 - VerifiedLab: Harnessing Knowns for Unknowns Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37923 - INFRAMIND: Infrastructure-Aware Multi-Agent Orchestration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11440 - Learning to Bound: Monotonic, Calibrated Neural Upper Bounds for MPE Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39305 - Where You Inject Matters: The Trust Region Effect in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38867 - Generating Critic-Guided Synthetic Experience in Latent World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39100 - Mind The Gap (MTG-AD): Dataset and Fine-grained Evaluation for End-to-End Inline Audio Descriptions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39955 - Upcycling Language Models for Multiple Specialized Domains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40091 - Spokes, not a Ring: Revisiting the Weekday Manifold in Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37796 - Trustworthy AI and Democracy: A Dual Taxonomy and Operational Framework of Democratic Risks and Contributions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.13565 - BURGER: Benchmarking and Understanding Robotic Generalization via Embodied Drawing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40532 - PCM: A Proof-Carrying Message Protocol for Verifiable Multi-Agent Communication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39109 - Before the Next Rollout: Diagnosing Skill Utility Shifts from Policy Updates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39358 - Non-Zero Radius: The Missing Component of Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39559 - METATRON: A Promptable Whole-Body Execution Layer for Humanoids Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38027 - Information-Theoretic Reliability--Safety Bounds and Finite-Alignment Dynamics in AI Knowledge Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38651 - Revisiting Over-refusal in Safety-aligned Large Language Models: A Representation and Optimization Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39802 - EPSBench: Benchmarking LLM Agents for Earnings Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38293 - Responsible Quantum Machine Learning for Medical Imaging: A Fairness Audit Across Sensitive Subgroups Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37819 - AI in the EGI e-infrastructure -- Past experiences and future strategies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40494 - Emergence of the transformer architecture as the score of entropic laws of random measures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39614 - Difference-Making without Making a Difference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24832 - DynaRev: Benchmarking Web Agents under Dynamic Goal Revision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40133 - World Model Science: Self-Organized Criticality, Weak Chaos, and Metastable Belief Dynamics in Long-Horizon LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17419 - IMPACT: Inverter-Informed Multimodal Learning for Photovoltaic Generation Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40418 - Rebuilding a Field's Open-Problem Catalog from the Literature: A Two-Layer Knowledge Graph, and Why Status Must Stay Proposed Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39641 - RoSeViT: Role-Separated Vision Transformers for ARC Visual Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13562 - Agent Transfer Protocol: Server-Mediated Agent-to-Agent Communication Architecture for the Agentic Web Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38398 - Neighborhood Elites: Quality-Diversity Search for Uncertainty Quantification in Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40278 - NLP-based Message Prioritisation for Opportunistic Routing: A Case Study of Nepal Earthquake Emergency Communication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37933 - Making Sense of Audience Change: Causal Attribution and Boundary Management on Xiaohongshu Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38026 - SHPRR: An Algorithm for Pure Exploration under Constrained Regret Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39837 - Context Compaction for World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38980 - AnyGoal: On World Model Generalization Beyond Expert Rollouts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26844 - NECA: Neighbor Event Curve Augmentation for Multi-Horizon ICU Deterioration Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40420 - Rubricon: Automated Rubric Generation and Refinement for LLM Evaluation and Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38220 - FARMS: A Verifiable Foundation for Automated Computational Science Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40560 - TorchTPU - A Hybrid Eager/Compiled Architecture for Native PyTorch Execution on TPU Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24161 - Aligning Misaligned Benchmarks for Single-View Novel View Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38349 - Event-SAMA: Language-Grounded Video Object Segmentation on Neuromorphic Event Streams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39676 - Curriculum-Based Deep Reinforcement Learning for Robust Autonomous Rocket Landing under Atmospheric Uncertainty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38636 - RoleFUZZER: User-Behaviour Fuzzing for Role-Specification Adherence in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38438 - DeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39265 - ARCANA: A Benchmark for Abstraction and Analogical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29271 - Towards Generalizing Pretrained All-Atom Representations to Unified Binder Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37994 - LLMs as Judges and Examinees for Medical Item Difficulty Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38402 - The Artificial Personality Model: Theory, Implementation, Measurement and Experimental Validation in Conversational Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38608 - Deogen: Automatic Benchmark Generation for Reasoning over Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38687 - Assessing feature scorer results on high-dimensional datasets with t-SNE Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39009 - Persona Learning from Feedback for Personalized AI Assistants Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38561 - Interventional Training Reduces Causal Bypass in In-Context Introspection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38911 - Uncovering Why LLMs Fail: From Internal Mechanisms to Adversarial Reasoning Trajectories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37369 - Decompose, Don't Expand: Capability-Independent AI Systems by Construction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38144 - Long-Term Agent Memory through Complementary Curation and Consolidation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39790 - Why Does Counterintuitive Likelihood Behavior Rarely Emerge in Tabular Anomaly Detection? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09593 - Learning unified control of intrinsic nonlinear spin dynamics in atomic qudits for magnetometry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28421 - DecompGym: Benchmarking LLM Agents on Designing Decomposition Algorithms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38175 - Answer-Only Disclosure: Private-Context LLM Assistance over Web APIs with a Leakage Ledger Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38126 - Distilling the Shape of Uncertainty: What On-Policy Distillation Learns and How to Predict It Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39020 - What Constitutes Food Similarity? Visual Representations and Retrieval in Indian Cuisine Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37867 - GenoBERT: A Language Model for Accurate Genotype Imputation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.00058 - PRISM: Personalized Item Representations in User History Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39175 - Learning response-aware patient dynamics for respiratory support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32782 - Retrieving from Your Own Mistakes: On-Policy Training of Embedding Models for Multi-Hop Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40409 - Hedge-Bench: Can Agents Reason Their Way to Better Predictions? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03918 - REALM: Identifying Minimal Task Assets for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39155 - Bridging Neural Representations and Symbolic Semantics in Audio Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40414 - KARMA: Training-Free Knowledge-Atomic Harness Evolution for Industrial Advertising Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39884 - Aligned Delta-Triplane Transformers as Occupancy World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.07338 - The View from Nowhere: Population-Centered Agent Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36660 - WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39278 - Learned Terminal Costs for Short-Horizon Model Predictive Control of Autonomous Trucks in Interactive Highway Traffic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40257 - Formal Specifications with Data-Driven Signal Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39007 - LiDAR-SHIELD: A Fully Dockerized Adversarial Robustness Assessment Framework for LiDAR-Based 3D Perception Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39848 - Is it my preference? Role Grounding Attack against Agent's Memory via Social Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38209 - Explainability-Aware Evaluation of Transfer Learning Models for IoT DDoS Detection Under Resource Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22488 - SCARL: Sequence Confidence-Aligned Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40407 - Multistep and Multivariate Time Series Explainability with GradientSHAP: A Wind Power Case Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40330 - Human--AI Interactions as First-Class Data: A Formal Interaction Model and Runtime for Explainable AI Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40006 - Where to Learn and How Far to Roll Out: Efficient Adaptive Training for GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39251 - Think Before You Act: Decision Gate for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38620 - Can AI Agents Interface Clinicians and Complex Models? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39681 - Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25184 - Rethinking Neural Thickets Without Weight Perturbations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40649 - GAAC: Lossless KV Compression for Bandwidth-Efficient LLM Inference on Personal Devices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38210 - Locating Sycophancy Across Training Stages in Open Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37788 - LLM-PowerTrace: A Dataset of Time-Resolved GPU Power Traces for AI Compute Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38315 - EnvOS: Auditing Computer-Use Agents When the World Moves On : Phenomenon-Based Task Construction, Certification, and Evidence-Based Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40246 - Collaborative AI agents for autonomous experimental research with solid-state quantum spins Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40589 - Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.30177 - Geometry Matters in Packed 3D Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38694 - Explore Where It Matters: Targeted Exploration for Efficient Rover Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38657 - LRMoE: Demand-Side Load Re-Calibration for Efficient MoE Training on Memory-Constrained Nodes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37720 - No Certificate, No Categorical Speech Act: A Brouwerian Assertibility Constraint for Public Reason Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03971 - Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.11311 - Heterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39682 - Bank-World: A Benchmark for Evaluating Agents on Banking Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39733 - Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39468 - PRISM: Pushing the Frontier of Deep Think via Process Reward Model-Guided Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02479 - Reasoning or Pattern Exploitation? Mechanistic Insights from RL-Trained Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39182 - Understanding Large Language Models as Numerical Optimizers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37932 - Agentic AI Reasoning and Learned Sampling for Task-Aware Projection Selection in Sparse-View CT: Predicting Hemodynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39003 - Bridging Semantics and Structure: A Theoretically Grounded Framework for Link Prediction on TAGs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40192 - VoiceLongMemEval: Do Assistants Remember How You Sounded? Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.00570 - Defining Operational Conditions for Safety-Critical AI-Based Systems from Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22118 - Comparing Human Role-Players and LLM-Simulated Clients in Online Counselling Training: An Analysis of Counselling Patterns Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40563 - MEV: A Multi-Event Video Dataset for Long-Take Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38241 - SkillCT: A Multidimensional Benchmark and Execution-Free Baseline for Agent Skill Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38147 - Learning to Model Optimization Problems from Solver Outcomes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.00442 - MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39714 - FARE: Factor-Aware Retrieval with Error-Guided Fusion for Retail Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40160 - Do Audio LLMs HEAR Pain? Tracing Acoustic Evidence from Speech to Language Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38570 - Membership Inference Attacks on Recommender System: A Survey Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2509.11080 - EUReCA: End-to-End Unified CBCT Reconstruction Across Clinical Acquisitions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37740 - MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.22677 - Prompt Lottery in LLM-as-a-Judge: Measuring and Mitigating Sensitivity to Syntactic Rephrasing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38076 - From the Transformer to a Formal Semantics of Coordinated Transformations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39735 - SemantiScene-Edit: Expert-Synthesized Supervision and Dual-Path Source Conditioning for Instruction-Based Video Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26015 - FlipJev: Fast Black-Box Red Teaming Finds Universal Adversarial Suffixes for Typed Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38895 - Reliability of LLM Judges for Evaluating Entity Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09554 - Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39497 - Heavy-Tailed Memory Traces in Long-Horizon Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00010 - Supervised Fine-Tuning for Reasoning Large Language Models: A Survey Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37681 - GAUSS: A Workload-Aware Analytical and Monte-Carlo Simulator for LLM Inference Serving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37989 - InterPol: De-anonymizing LM Arena via Interpolated Preference Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15220 - BridgeRouter: Gain-Aware Instance Routing over Cross-Modal Bridge Portfolios Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38152 - Jacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16407 - LLM Agent-Based Design of RISC-V CPUs with FPGA-in-the-Loop Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39570 - Measuring Where Intent Gets Lost in Agentic Smart Contract Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37830 - SkillMem: Compact External Skill Memory for Latent Multi-Agent Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37935 - Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12655 - Value Probes: Learned Value Functions for Beam-Search Red Teaming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38526 - Dungeons & Dragons Encounter Analysis with Semi-Random Simulation in Foundry VTT Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38975 - When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07313 - The Hitchhiker's Guide to System 1 Models: Fast Decision-Making Beyond LLMS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33775 - Strategic Integration of Artificial Intelligence in the C-Suite: The Role of the Chief AI Officer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.10247 - Cord: Confidence-Anchored Order Residual Decoding for Masked Diffusion Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39372 - Predicate Neuron: Differentiable Quantization of Predicate Relations in Gradient-based Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37727 - Escaping Path Mirages in Offline Goal-Conditioned Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40130 - PromptSense: Sentiment-Aware Mental Health Chatbot with Dynamic Prompting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38044 - EPC-RawDC: Equivariant Physics Constrained 3D Diffusion with Raw Data Consistency for CBCT to CT Image Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40046 - "It Would Make a Geordie Feel at Home": Regional Accent Perceptions and Speech Accommodation in Voice AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38005 - Skeleton Coding: Program Structure as a Specification for Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38214 - Reaction precedents extend retrosynthetic prediction beyond training coverage Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40249 - From Legacy Fortran to Portable Kokkos: An Autonomous Agentic AI Workflow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.12443 - Auditable Belief Updates as a Missing Safety Layer for LLM-Powered Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38869 - SocialArena: Evaluating Social Intelligence in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39247 - The Role of Self-Concept In Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39795 - Gym-Anything for Robotics: Scaling physical simulations with digital agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40565 - When Does Closed-Loop Curriculum Adaptation Help GRPO? An Analysis on Countdown Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39056 - SymKL: A Unified Representation-Space Measure of Signal Degradation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39403 - Design the Feedback, Not Just the Reward: Environments for Open-Ended Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27906 - Industrialized Deception: The Collateral Effects of LLM-Generated Misinformation on Digital Ecosystems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21963 - OPERA: OPamp Design by an Expert-Taught Reasoning Agent, from Specifications to Layout Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39395 - Pharos-ESG: A Framework for Multimodal Parsing, Contextual Narration, and Hierarchical Labeling of ESG Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.16417 - AI-Driven Digital Twin Framework for Warehouse Logistics Automation Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38101 - Latent Decision Flow Rewards for Clinical Guideline Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38709 - Localizing Concepts in Visual Autoregressive Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40061 - Self-Supervised Latent Action-Conditioned World Modeling for Time Series Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37963 - Beyond Low-Pass Dynamics: Frequency-Selective Spiking Reservoirs with Resonant Neurons Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37906 - How to Loop Your Transformer: Loop Scaling, Specialization, and Parallel Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40325 - Generative artificial intelligence prompting strategies among Chinese university students across academic tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39571 - ATLAS: Dual-Horizon Diagnostic Evaluation for Tool-Use Agents in Meituan Xiaotua Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30685 - TrussTutor-Bench: Benchmarking large language models on solution accuracy, sycophancy, and error detection in statics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38917 - Discovering Jailbreaks via Curriculum of Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38833 - EpiAgent: Epistemic Self-Play for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40227 - Think Twice: The Metis-1.6 Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37903 - Accelerating Nonlinear MPC by Behavior Cloning with Separated Timescales: Application to Nuclear Reactor Load-Following Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38496 - LLM-Integrated Bayesian State Space Models for Multimodal Time-Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.20952 - Game-Theoretic Foundations for Undiscounted Bisimulation Metrics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38313 - What Can Firms Do in the Face of Model Distillation? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38088 - Hippo: Training-Free Agent Self-Evolution via Hippocampal Replay Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24453 - Proving and Improving the Platonic Representation Hypothesis with JEPAs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39302 - ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.22016 - Integrating Heterogeneous Echocardiography AI Outputs in Language Space: Learnable Late Fusion with a Supervised LLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39464 - What Breaks When Facts Become Stories? The Distortions Source-Agreement Metrics Miss When Models Retell Real Events Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39500 - Integrated Feature Selection for classification and Representation Learning with Group-Lasso Siamese Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39499 - TERRA: Task-Oriented Edge AI for Regional Fire Detection with Identity-Free Reporting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37909 - Beyond fabrication: Misattributed numbers in papers written by AI research agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38691 - Evaluating Visual Realism of AI-Generated Videos with Eye Tracking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38825 - SAG-Sep: Sparse Augmented Graphs and Onion-Guided Search for Rounded Capacity Cut Separation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37952 - Distributional Reward Calibration and Budget-Neutral Credit Assignment for Multimodal RLVR Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40250 - Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39264 - DiG-bench: Discovery in Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12593 - What Actually Matters? A Paired Evaluation of Inference Settings for $\pi_{0.5}$ on BEHAVIOR-1K Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37917 - A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38568 - ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.14326 - Goal-Aware Dynamic Multi-Agent Collaboration for Long-Horizon Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39193 - Masked Erosion: How Acceptance Gates Lose Redundant Safeguards in Self-Improving Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38392 - Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38851 - TreasuryQA Bench: Can AI Agents Work an Archive of Scanned Financial Records? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38924 - Predicting What Answer Engines Cite: Open Decision Models, Rerankers and a Distilled 4B Student on Ten Engines under Controlled Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38090 - Compute Has Shape: Self-Morphing the Internal Computation of Frozen LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38382 - Training Natural Schemers: RL Can Amplify Oversight-Conditional Behavior Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26551 - WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38352 - GenAI as an 'Invisible Hand' in Opinion Dynamics: Evidence from a Group-Level Simulation Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37689 - Reinforcement Learning for the Game of Balatro: A Fast Simulator and Two-Policy Training Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39049 - ThinkJev: One Thought, Every Budget for Calibrated Typed Decisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37732 - Where Do Vision Language Models Fail at 3D Reasoning? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39639 - Towards Batch-to-Streaming Deep Reinforcement Learning for Continuous Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.08588 - When More Planning Hurts: Learned Planners for World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37891 - TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40613 - Prompt-agnostic Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37683 - Multi-Agent LLMs for Adaptive Acquisition in Bayesian Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28959 - Only Accepted Tokens Count: An Energy Accounting of Speculative Decoding Under Latency Targets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40287 - Extremely Sparse-View Computed Tomography from 2D Projections via Pose-Aware Diffusion Priors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38319 - Representation Complexity Along Learning Trajectories: Trading Width for Precision and Time Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39027 - There Is No Free Lunch in RLVR: Every pass@1 Gain Has a pass@k Price Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39295 - EARS-Info: Information-Aware Event-Driven Reallocation for Multi-Robot Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38040 - Beyond Selected Breakthroughs: Evaluating Language Models on Randomly Sampled Mathematical Conjectures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40382 - How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40516 - Generalizable dose denoising using diffusion transformer framework for pencil beam scanning proton therapy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.04467 - Exploring the Potential of Symbolic Regression in Precision Livestock Farming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39839 - An Analysis of Artificial Intelligence Adoption in NIH-Funded Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07424 - Making Smart Homes Fit for Autistic Children: Family Work and Monitored Independence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38008 - Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13406 - Estimating Implicit Expected Log Density Ratios Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38151 - From Intent to Improvement: Agentic Dataset Search for Better Model Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39608 - Radiology Guideline-derived Decision Graph for Efficient Clinical Decision Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40327 - NeuroBridge: Bio-Inspired Self-Supervised EEG-to-Image Decoding via Cognitive Priors and Bidirectional Semantic Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.06836 - DuQUAD: A Dual-View Framework with Quality-Aware Evidence Pruning for Multi-Document Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37701 - Verification-Guided Retrosynthesis: Reaction Feedback and Evidence Timing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38245 - AegisFlow: Training-Free Non-Myopic Path-Safe Guided Flow Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39825 - Robust Taylor-Lagrange Control for Safety-Critical Systems with Guaranteed Feasibility Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.20076 - Latent Prediction Yields Cross-Subject Alignable Representations in Sensory-Evoked fMRI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40280 - Scaling Lean Theorem Proving for Real-World Code Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38174 - Cross Lingual Abstractive Summarization for Marathi Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38267 - The generative paradox: the Anti-Prompt paradigm for human capability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40151 - Where the Error Lives: Spectral Representations of Learned Kohn-Sham Hamiltonians Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37843 - SpaceAct: Benchmarking 3D Spatial and Temporal Reasoning via Closed-Loop Action and Active Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38405 - Beyond LLM Wrappers: Context Engineering and the Three-Engine Architecture for Reliable Financial AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39230 - Convex-SKM-Net: Low-Latency Block Halfspace Corrections for Neural Convex Constraint Satisfaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38197 - Autonomous Quantum Measurement with Agentic AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38850 - Referential Regimes: Transformation-Based Identity Profiles for Neutral Substrates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16152 - When to Assist and What to Suggest: Joint Gating and Memory-Grounded Hint Generation in One Compact Decoder Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40611 - Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.03672 - Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38681 - Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39122 - Exploration and Exploitation Errors Are Measurable for Language Model Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13151 - Dual Exam: Controlled Evaluation of Multimodal Agents and World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31066 - ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Caching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04510 - Reward-Adaptive Co-Evolution of Policy and Rubric Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40096 - GARDEN: Generalist Autonomous Reward Design Through Evidence Navigation for Cooperative Multi-Agent Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37926 - Scaling Mathematical Proof Supervision from Structured Textbooks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40394 - Hybrid AI Patterns: Thirteen Ways to Couple Language Models with Rules, and How to Choose Among Them Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40036 - What Makes Medical Examination Items Difficult? Using Large Language Models to Explore Patterns Associated With Empirical Item Difficulty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39373 - EvoTeam: Multi-Agent Collaboration via Evolving Teams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39813 - Where Planning Changes the Outcome of Orbital Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37686 - Beyond Similarity Search: Knowledge Graph Metadata Enrichment for Enterprise Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37728 - Benchmarking decision models against generative large language models on medical multiple-choice questions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38448 - Data Provenance and Ethics in the Curricula of U.S. Health AI Education Programs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39606 - The Code Behind the Layout: AI Agents for Analog Layout Generators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38426 - On the Fundamental Limits of Prefill-Based Decoding Length Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40541 - MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02260 - When Do Causal World Models Help Modular LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00012 - Category-Anchored Large Language Models for Next POI Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39518 - DEG: Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39512 - Post-Training Large Language Models with LLMON Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38120 - CHORD: Cross-Model Hallucination Detection via Relational Graph Discrimination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38314 - The Verification Crisis: Expert Perceptions of GenAI Disinformation and the Case for Reproducible Provenance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02100 - EmbodiExp: Compositional Experience Transfer for Embodied Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39180 - FACTS-MAS: A Multi-Agent Architecture for Adaptive Forecasting from Heterogeneous Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38225 - AtomTree: A Hierarchical Framework for State-Aware Embodied Instruction Following with LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38744 - Retrieval as Traversal: Value-Indexed Memory for Stateful Long-Context Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40545 - When Context Changes: Understanding Update Failures in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38866 - Learning to Formulate: Agentic Hardware-Software Co-Design of AI Infrastructure through Progressive Optimization and Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39380 - Rethinking Group Recommender Systems in the Era of Generative AI: From One-Shot Recommendations to Conversational Group Decision Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.00535 - MedGemma vs GPT-4: Open-Source and Proprietary Zero-shot Medical Disease Classification from Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.23304 - One Vector or Many? Clustered Optimal-Transport Steering under Quantization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40055 - Statistical Detection of Positional Bias in LLM-Based Recommender Systems: Methodologies and Empirical Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37962 - Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.12401 - Learning Lotteries with Minimal Stakeholder Violations from Membership Queries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37828 - Tracekit Box: Running AI Agents in Micro-VMs Where Every Way Out Is Decided and Signed Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38458 - Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24069 - Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Ground Truth Is Unavailable Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04127 - Why Speculative Decoding Works Better Than Predicted on Sparse MoE Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38981 - Finding Is Not Returning, Returning Is Not Reconstructing: A Multi-Dimensional Evaluation of Agent Social Re-entry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39781 - Multistatic ISAC with Deep Learning-Based Clutter Suppression for 5G and Beyond Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40586 - Learning Scientific Trajectories to Predict Future Biomedical Discoveries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38719 - Aligning Autoresearch: Co-Improvement between Agents and Humans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38882 - FVH-Bench: Evaluating Image Generator Safety Beyond Overtly Harmful Imagery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37722 - Cassette-Editor: A Video Editing Agent That Edits the Way You Do Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37690 - Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39483 - PAPERBENCHX: Can AI Reproduce Science Across Disciplines? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39744 - From extreme weather to agricultural consequences with agentic AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40641 - OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37739 ## Community - How We Took Over ChatGPT Accounts Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/31/how-we-took-over-chatgpt-accounts/ - datasette-llm 0.1a9 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/31/datasette-llm/ - ChatGPT and Codex usage limits merging Source: hacker-news Topic: General (+AI) URL: https://help.openai.com/en/articles/20001625-understanding-chatgpt-and-codex-usage-limits - Anthropic takes steps to block Claude from reverse-engineering video games Source: hacker-news Topic: General (+AI) URL: https://mashable.com/tech/anthropic-takes-steps-to-block-video-game-cloning-and-reverse-engineering - Anthropic blocks users for anything touching training larger models Source: hacker-news Topic: General (+AI) URL: https://twitter.com/jiahaoshao1/status/2116475922190922088 - GPT-5.6 Sol can beat Factorio on peaceful mode Source: hacker-news Topic: General (+AI) URL: https://ryanmadden.net/gpt-56-beats-factorio/ - Anthropic orders AI tool Claude to stop remaking video games Source: hacker-news Topic: General (+AI) URL: https://www.gamedeveloper.com/programming/anthropic-appears-to-have-ordered-ai-tool-claude-to-stop-remaking-video-games - Malware uses LLMs to rank victims by how much they're worth Source: hacker-news Topic: General (+AI) URL: https://blog.talosintelligence.com/appraisal-by-ai-model-driven-victim-prioritization-in-the-volta-infostealer/ - AI startup hacks Anthropic, gains access to employee details, internal messages Source: hacker-news Topic: General (+AI) URL: https://www.indiatoday.in/technology/news/story/ai-startup-hacks-anthropic-in-12-hours-gains-access-to-employee-details-and-internal-messages-3025452-2026-10-26 - Anthropic's Claude AI blocks video game cloning and reverse-engineering Source: hacker-news Topic: General (+AI) URL: https://www.tomshardware.com/tech-industry/artificial-intelligence/anthropics-ai-model-is-now-blocking-attempts-at-video-game-recreation-and-cloning-users-also-claim-non-malicious-generic-reverse-engineering-tasks-are-blocked - Show HN: A language model that lives in a boot sector Source: hacker-news Topic: General (+AI) URL: https://github.com/kerlenton/bootgpt - Why Anthropic's Filing Crushed Tech Stocks Source: hacker-news Topic: General (+AI) URL: https://www.thebignewsletter.com/p/why-anthropics-filing-crushed-tech - Do the math: How we took over ChatGPT accounts Source: hacker-news Topic: General (+AI) URL: https://www.parameter.ai/labs/we-found-a-gap-at-openai - Let’s Build a Brain Source: lobsters Topic: General (+AI) URL: https://aatishb.com/myriad/lets-build-a-brain/ - OpenAI raises less than half of $30B target Source: hacker-news Topic: General (+AI) URL: https://www.wsj.com/tech/ai/openai-raises-less-than-half-of-30-billion-target-in-latest-round-91aecdc5