AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchMore Features Are Not More Evidence: Limits of Training-Free Human Activity Recognition with Jev
arXiv:2609.36154v1 Announce Type: new Abstract: General-purpose models promise sensor-based decisions without training a task-specific classifier, which could reduce the dependence of Human Activity Recognition (HAR) on…
- arXiv cs.AIagentsPrincipled Thoughts for Latent Recursive LLM Systems
arXiv:2609.36159v1 Announce Type: new Abstract: Large language models can reason in continuous space instead of decoded text, by recurring on their own hidden states or by passing those states between agents, while train…
- arXiv cs.AIresearchFigAct: Turning Scientific Figures into Active Canvases for Explanation
arXiv:2609.36190v1 Announce Type: new Abstract: Scientific figures are designed to communicate information visually, yet MLLMs typically explain them by translating their visual content back into text. This requires read…
- arXiv cs.AIresearchAn Empirical Study and Assessment of EU AI Act Compliance Checkers
arXiv:2609.36228v1 Announce Type: new Abstract: The EU AI Act introduces extensive compliance requirements for organizations that develop, deploy, or integrate AI systems. Many of these requirements are directly relevant…
- arXiv cs.AIagentsMERID: Multimodal Exploration via Recursive Self-Improvement Agents for Major Depression Analysis
arXiv:2609.36235v2 Announce Type: replace Abstract: Major depressive disorder (MDD) severely impacts daily activities and quality of life. Detecting MDD involves multimodal data, such as interview recordings and sensor m…
- arXiv cs.AIagentsChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning
arXiv:2609.36238v1 Announce Type: new Abstract: A goal that is close in space can be far away in time. Obstacles, terrain, and the agent's own capabilities determine how long it takes to get there. Yet, critics in contra…
- arXiv cs.AIresearchCoRe: Co-Evolving Reward Models for Mitigating Latent Reward Hacking in Video Diffusion Models
arXiv:2609.36245v1 Announce Type: new Abstract: Latent reward models (LRMs) enable efficient alignment of video diffusion models by scoring intermediate states directly in latent space. However, we find that optimizing a…
- arXiv cs.AIresearchTowards Mitigating Deceptive Safety Alignment in Large Reasoning Models
arXiv:2609.36254v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) are commonly trained with reinforcement learning (RL) to improve their generation of chain-of-thought (CoT) reasoning before producing final a…
- arXiv cs.AIresearchOTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models
arXiv:2609.36264v1 Announce Type: new Abstract: Reliable evaluation of large language models (LLMs) is essential for their development and deployment, yet is often costly, risky, and difficult to perform safely online. W…
- arXiv cs.AIresearchFrom Surfaces to Volumes: Registered Geometry for Protein Representation Learning
arXiv:2609.36277v1 Announce Type: new Abstract: Existing protein geometry models typically represent molecular surfaces using local geometric features such as sampled points, normals, and curvature. While effective for c…
- arXiv cs.AIagentsIllusory Truth or Mere Exposure? Model-Dependent Repetition Effects in LLM-Based Social Media Simulations
arXiv:2609.36278v1 Announce Type: new Abstract: Generative agent-based models (GABMs) are increasingly used to simulate social media dynamics, including misinformation spread. For such social simulations to be valid prox…
- arXiv cs.AIagentsCheatBench: Measuring Reward Gaming in AI Agents
arXiv:2609.36308v1 Announce Type: new Abstract: Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recent incidents and cont…
- arXiv cs.AIagentsStateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents
arXiv:2609.36319v1 Announce Type: new Abstract: Despite the recent success of coding agents built on large language models, it remains challenging to run them over long horizons, since every observation is appended to th…
- arXiv cs.AIresearchTowards an AI Software Factory for Data Systems
arXiv:2609.36323v1 Announce Type: new Abstract: AI-assisted coding tools deliver significant acceleration of coding, but only limited impact across the end-to-end software development lifecycle (SDLC)--an Amdahl's law ef…
- arXiv cs.AIresearchPILLAR: Private Inverted-Index Lexical Lookup for Augmented Retrieval
arXiv:2609.36326v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) hands the user's query to whoever hosts the corpus. We propose PILLAR, a Privacy-Preserving RAG (PPRAG) system based on Private Inf…
- arXiv cs.AIresearchThuRunel: Dynamic Decoupling for Structured Advisory Dialogue
arXiv:2609.36340v1 Announce Type: new Abstract: High-stakes advisory domains such as medical aesthetics, legal consultation, and educational planning exhibit a two-phase structure. The early phase requires empathetic eli…
- arXiv cs.AIresearchHyperZip: Efficient Data Compression through Personalized Diffusion LLMs with Hypernetworks
arXiv:2609.36357v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential for lossless data compression, but existing approaches are constrained by the high computational cost and low throu…
- arXiv cs.AIresearchBetter Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruning
arXiv:2609.36359v1 Announce Type: new Abstract: Graph-based approximate nearest neighbor search (ANNS) is widely used for large-scale semantic search. Its indices are constructed primarily based on geometric relationship…
- arXiv cs.AIagentsEngineering Simplicity: Simple Mechanism Interfaces Steer LLM Agents
arXiv:2609.36365v1 Announce Type: new Abstract: Can interaction formats and textual scaffolds help large language model (LLM) agents make better decisions, and do better decisions come with better explanations? We study…
- arXiv cs.AIresearchSupport-Set Target Leakage in Relational Foundation Models during In-Context Learning: Impact, Detection, and Mitigation
arXiv:2609.36384v1 Announce Type: new Abstract: Relational in-context learning (ICL) conditions predictions on the labeled support examples and their linked tables, creating a failure mode when the support set contains t…
- arXiv cs.AIresearchPersona Dosing: Calibrated Activation Steering for Graded Trait Control
arXiv:2609.36388v1 Announce Type: new Abstract: An activation-steering coefficient sets intervention strength, but requesting a particular degree of persona expression requires a behavioral scale. We study persona dosing…
- arXiv cs.AIagentsARCagent: An Adaptive Retrieval Calibration Agent for Clinical Question Answering
arXiv:2609.36392v1 Announce Type: new Abstract: In diseases where clinical guidelines are incomplete, contested, or mutually contradictory, knowledge completeness and dynamic conflict-aware synthesis are two safety-criti…
- arXiv cs.AIagentsFrom Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles
arXiv:2609.36406v1 Announce Type: new Abstract: Cell Painting is a high-content morphological profiling assay widely used for phenotype-based biological inference, with mechanism of action (MOA) prediction as a central a…
- arXiv cs.AIresearchSupport-Set Target Leakage in Relational Foundation Models during In-Context Learning: Model Dependence and Evaluation Reliability
arXiv:2609.36417v1 Announce Type: new Abstract: Relational in-context learning (ICL) uses labeled support examples and their linked relational context to predict labels for new queries. This creates a failure mode when t…
- arXiv cs.AIresearchThe Safety Operator: Modulating the Expression of Safety Instructions via Spectral Optimization
arXiv:2609.36434v1 Announce Type: new Abstract: Context tokens in a transformer-based language model can be absorbed into the model's weights as a multiplicative operator. We study this operator in the setting of safety…
- arXiv cs.AIresearchBits Under ZK-LLM: Evaluating Zero-Knowledge-Friendly Quantization for Verifiable Private LLM Inference
arXiv:2609.36437v1 Announce Type: new Abstract: Zero-knowledge proofs are emerging as a promising approach for enabling private, verifiable LLM governance and auditing, where regulators, users, and auditors need to verif…
- arXiv cs.AIresearchRethinking Reasoning Paths as Phase-Structured Trajectories
arXiv:2609.36461v1 Announce Type: new Abstract: Large language models often improve problem-solving performance by generating multi-step reasoning paths, yet how to analyze the hidden states along these paths remains unc…
- arXiv cs.AIresearchGoing Beyond State-Reaching: Learning Abstractions for Intrinsically Motivated Option Discovery
arXiv:2609.36473v1 Announce Type: new Abstract: Temporal abstraction via options can improve exploration in large environments. However, existing option discovery algorithms find subgoals that target all aspects of the s…
- arXiv cs.AIagentsLearning to Harvest Without Collapse in a Regenerative Commons: A Lagrangian Framework
arXiv:2609.36478v1 Announce Type: new Abstract: The tragedy of the commons poses a multi-agent safety problem: reward-seeking agents can deplete a shared resource, and cooperation among its users does not itself specify…
- arXiv cs.AIresearchHuman-AI Collaboration: From Paradoxes to Patterns
arXiv:2609.36481v1 Announce Type: new Abstract: Evidence shows that humans and AI systems perform better together, by collaborating, than alone. This paper examines two key design dimensions of human-AI collaboration (au…
- arXiv cs.AIresearchAVIO: Learning to Add and Remove Sounding Objects in Audiovisual Scenes
arXiv:2609.36503v1 Announce Type: new Abstract: Adding or removing a sounding object requires coordinated changes to visual content and sound while preserving the surrounding scene. Yet paired supervision for localized n…
- arXiv cs.AIagentsBRIDGE: Bilevel Retrieval-Credit-Aware Agentic Reinforcement Learning
arXiv:2609.36505v1 Announce Type: new Abstract: Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by learning to interle…
- arXiv cs.AIagentsMAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems
arXiv:2609.36556v1 Announce Type: new Abstract: Recent studies report that LLM-based multi-agent systems (MAS) fail at rates of 41%-87%, yet to our knowledge, no benchmark to date supports systematic anomaly detection (A…
- arXiv cs.AIresearchVisual sensitivity is not claim retractability: persistence-aware credit assignment for multimodal reinforcement learning
arXiv:2609.36572v3 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further encourage policies…
- arXiv cs.AIagentsDivide and Inject: Can Agents Reconstruct an Indirect Prompt Injection from Fragments?
arXiv:2609.36576v1 Announce Type: new Abstract: Agentic systems are now being widely used to orchestrate tools and reason over long contexts. However, the improving capabilities of the large language models powering thes…
- arXiv cs.AIagentsSafeCoEvo: Co-Evolving Safety Harnesses and Guards for LLM Agents at Test-Time
arXiv:2609.36580v2 Announce Type: replace Abstract: LLM agents deployed in real-world environments continually encounter new tasks and safety risks, while execution feedback typically becomes available only after each ta…
- arXiv cs.AIresearchMemEvo: Automatic Discovery of Streaming Video Memory Mechanisms
arXiv:2609.36581v1 Announce Type: new Abstract: Query-agnostic streaming video understanding requires vision-language models to continuously compress an indefinitely growing visual stream into a bounded memory before fut…
- arXiv cs.AIresearchTransformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
arXiv:2609.36585v1 Announce Type: new Abstract: Pretrained transformers use little of their depth to follow references in context. Thirteen base models reliably follow only 1.4-3.6 lines, and extra pretrained loops add l…
- arXiv cs.AIresearchSAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation
arXiv:2609.36601v1 Announce Type: new Abstract: On-policy distillation (OPD) reduces train-test state mismatch by training a student on its own generated trajectories, but weak students may visit teacher-misaligned prefi…
- arXiv cs.AIagentsMulti-Channel Mitigation of Source-Trust Shortcuts in Fact-Checking RL Agents
arXiv:2609.36611v1 Announce Type: new Abstract: Retrieval-augmented fact-checkers often receive a reliability label, such as HIGH or LOW trust, for each evidence source. These labels should adjust the model's confidence…
- arXiv cs.AIresearchNeural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge
arXiv:2609.36620v1 Announce Type: new Abstract: Structural reasoning, the ability to recognize and make inferences over the relational structure between objects and concepts, is a hallmark of human cognition, yet prevail…
- arXiv cs.AIresearchDualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors
arXiv:2609.36624v1 Announce Type: new Abstract: Joint speech-gesture synthesis must coordinate two modalities despite limited paired data. Existing approaches often lack bidirectional interaction, have limited language c…
- arXiv cs.AIagentsSemantic Projection for Continual Self-Evolution of Language Agents
arXiv:2609.36626v1 Announce Type: new Abstract: Language-model agents increasingly rely on persistent natural-language skills to adapt beyond their frozen model parameters. When a shared skill is repeatedly revised from…
- arXiv cs.AIagentsDistilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses
arXiv:2609.36630v1 Announce Type: new Abstract: Modern agents increasingly rely on memories, tools, and execution logic, so their competence extends beyond model parameters. This shift exposes a limitation of conventiona…
- arXiv cs.AIresearchRankBuffer: Efficient Ranking-Based Rewards for Open-Ended Generation
arXiv:2609.36652v1 Announce Type: new Abstract: Open-ended generation lacks canonical answers, making pointwise rewards difficult to calibrate for group-based reinforcement learning. Directly ranking same-query rollouts…
- arXiv cs.AIresearchFineSID: Scalable and Efficient Semantic Identifier Learning for Generative Recommendation
arXiv:2609.36670v2 Announce Type: replace Abstract: A critical prerequisite of generative recommendation is designing semantic identifiers (SIDs) that are both scalable to large item sets and efficiently learnable. Exist…
- arXiv cs.AIresearchFairDiff: Mitigating the Self-Reinforcing Matthew Effect in Diffusion Recommender Models
arXiv:2609.36671v2 Announce Type: replace Abstract: While the "Matthew Effect" and filter bubbles are widely recognized outcome-level biases in recommender systems, we reveal that Diffusion Recommender Models (DRMs) uniq…
- arXiv cs.AIagentsMLToolBench: Learning Tool-Augmented Agents for Machine Learning Development
arXiv:2609.36679v2 Announce Type: replace Abstract: Machine learning engineering (MLE) agents have made substantial progress, but learning through ML experimentation remains costly in time and computation. Synthetic envi…
- arXiv cs.AIresearchJudgeProfile: Understanding and Steering Subjectivity in LLM Judges
arXiv:2609.36705v2 Announce Type: replace Abstract: LLM judges are inherently subjective, often favoring different responses in pairwise comparison when neither option is objectively wrong. To study this subjectivity, we…
- arXiv cs.AIagentsCan AI Scientists Change Their Minds? Prior-Evidence Conflict in Synthetic Universes
arXiv:2609.36726v1 Announce Type: new Abstract: Can a scientific agent distinguish a law it inferred from evidence from one it merely recognizes? We introduce Synthetic Universes, a controlled benchmark that pairs canoni…