AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsLLM-Guided Transformation of Non-Critical Driving Scenes into Safety-Critical Scenarios Using Augmented Reality
arXiv:2609.20318v1 Announce Type: cross Abstract: Testing Autonomous Driving Systems (ADS) requires realistic safety-critical scenarios, but collecting such data from real-world driving is costly and unsafe. This paper p…
- arXiv cs.AIagentsSTR-Agent: An LLM-Driven Agent for QoS-Aware Routing in LEO Satellite Networks
arXiv:2609.20347v1 Announce Type: cross Abstract: LEO satellite networks feature dynamic topologies, time-varying links, and diverse service requirements, which make conventional routing schemes difficult to support fine…
- arXiv cs.AIresearchAccelerating Sharded Data Parallelism at Scale with Federated Learning
arXiv:2609.20359v1 Announce Type: cross Abstract: The symbiotic scaling of artificial intelligence models and high-performance computing systems continually creates algorithmic challenges in their convergence. Foundation…
- arXiv cs.AIresearchXeno-Interpretability: Investigating the Alien Minds of LLMs
arXiv:2609.20408v2 Announce Type: replace-cross Abstract: Large language models are usually interpreted through concepts that humans already possess: truthfulness, refusal, deception, personality, harmfulness, and relate…
- arXiv cs.AIresearchStress-testing Alignment Midtraining
arXiv:2609.20412v1 Announce Type: cross Abstract: When aligning frontier models through post-training techniques, it is not possible to directly demonstrate all of the behaviours we want a model to exhibit in all possibl…
- arXiv cs.AIresearchTouchSight: Bare-Handed Tactile Prediction from Egocentric Video via Generative Visual Augmentation
arXiv:2609.20414v1 Announce Type: cross Abstract: Tactile signals provide direct contact and force measurements that are essential for understanding physical interactions and enabling dexterous robotic manipulation. Howe…
- arXiv cs.AIresearchSCGFM-ART: Amortized Relational Transport for Structure-Centric Graph Foundation Models
arXiv:2609.20419v1 Announce Type: cross Abstract: Graph foundation models (GFMs) aim to learn transferable representations across severely heterogeneous graph domains. However, severe domain shifts in topology, graph sca…
- arXiv cs.AIresearchWhen Do Language-Grounded Explanations Help? A Graph-Bottleneck for Farm Monitoring Interpretable Sheep Facial Pain
arXiv:2609.20427v1 Announce Type: cross Abstract: Automated pain recognition from facial expression could make continuous welfare assessment practical in sheep, but adoption depends on trust: a stockperson cannot act on…
- arXiv cs.AIresearchA Mathematical Model of Motivated Emotional Mind - Cognitive Embodied System
arXiv:2609.20437v1 Announce Type: cross Abstract: This article presents a mathematical model of the Motivated Emotional Mind cognitive architecture developed for embodied intelligent systems. Such a system learns to main…
- arXiv cs.AIresearchFingerprinting Multimodal Large Language Models
arXiv:2609.20457v1 Announce Type: cross Abstract: While multimodal large language models (MLLMs) enable a wide range of image-text reasoning tasks, recent incidents indicate that they are vulnerable to illicit deployment…
- arXiv cs.AIresearchDeep Learning-Based Classification of Cognitive and Resting States Using Electroencephalography Signals
arXiv:2609.20467v1 Announce Type: cross Abstract: The categorization of cognitive and resting states derived from electroencephalography (EEG) signals is crucial for comprehending fluctuations in brain activity linked to…
- arXiv cs.AIresearchgreCAPTCHA: Assessing Understanding as Evidence of Research Authorship Under Generative AI
arXiv:2609.20481v1 Announce Type: cross Abstract: Conferences, journals, funders, schools, and universities are struggling with a surge of potentially AI-generated submissions from ostensibly human authors, who may not h…
- arXiv cs.AIresearchEdustories: A Collection of Real-world Case Studies from Classroom Practices
arXiv:2609.20484v1 Announce Type: cross Abstract: Despite the widely recognized potential of AI in education, most prior work has focused on individualized student assistance. In contrast, the majority of educational pra…
- arXiv cs.AIagentsModel-Agnostic and Language-Agnostic Voice Pipeline Improvement for the Agriculture Domain
arXiv:2609.20504v1 Announce Type: cross Abstract: FarmerChat is Digital Green's AI-powered agricultural advisory assistant for smallholder farmers, who access it in their own language through text, voice, or photographs.…
- arXiv cs.AIagentsMitigating Retaliatory Algorithmic Collusion in Repeated Games
arXiv:2609.20548v1 Announce Type: cross Abstract: Reinforcement learning agents trained to maximize their own reward in repeated interactions can converge to supra-competitive outcomes resembling explicit collusion, with…
- arXiv cs.AIresearchAccelerating Visual Policy Learning with Sampling-Based Model Predictive Control
arXiv:2609.20575v1 Announce Type: cross Abstract: Learning visual policies for locomotion and manipulation requires coordinating contact with the environment and can incur substantial computation and GPU memory costs. Fi…
- arXiv cs.AIresearchInference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape
arXiv:2609.20614v1 Announce Type: cross Abstract: Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced by recent sandbox e…
- arXiv cs.AIagentsA Simulation Platform for AUV Fault Recovery: Exploring LLM-Based Diagnostic Strategies
arXiv:2609.20620v1 Announce Type: cross Abstract: Autonomous underwater vehicles (AUVs) operating beyond reliable communications must recover from failures without human intervention. We investigate an architecture in wh…
- arXiv cs.AIagentsChronicle: Cut-Point Replay for Regression Testing of LLM Agents
arXiv:2609.20625v1 Announce Type: cross Abstract: Large language model responses are non-deterministic, so failures in LLM agents are hard to reproduce: a failure depends on inference that is not bitwise reproducible, on…
- arXiv cs.AIresearchHIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface
arXiv:2609.20659v2 Announce Type: replace-cross Abstract: Large-scale vision-language-action (VLA) models provide powerful priors for robot manipulation, yet adapting them to a specific deployment remains challenging. Su…
- arXiv cs.AIagentsDon't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
arXiv:2609.20715v1 Announce Type: cross Abstract: Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies loss only to agent-authored action tokens, using env…
- arXiv cs.AIresearchLarge Language Models as Falsifiers for Cyber-Physical Systems
arXiv:2609.20752v1 Announce Type: cross Abstract: Falsification searches for counterexamples to formal specifications in cyber-physical systems (CPS). With specifications written in Signal Temporal Logic (STL), falsifica…
- arXiv cs.AIagentsPrediction-Powered Smoothing and Validation for Disaggregated AI Evaluation
arXiv:2609.20758v1 Announce Type: cross Abstract: Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in deployed agents. Exh…
- arXiv cs.AIagentsSemantic Action Graph: A Shared Representation for Agent Grounding and Human Interpretation of Sports Highlights
arXiv:2609.20768v2 Announce Type: replace-cross Abstract: Generative agents are increasingly used to select and narrate video highlights, but they typically operate over unstructured or frame-level representations. Their…
- arXiv cs.AIresearchGeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies
arXiv:2609.20776v1 Announce Type: cross Abstract: Action chunking is widely used for action generation and execution in Vision-Language-Action (VLA) policies, yet existing approaches commonly use a fixed action horizon.…
- arXiv cs.AIresearchHarm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations
arXiv:2609.20779v1 Announce Type: cross Abstract: Safety evaluations for large language models rely on surface-form classifiers that report declining harm scores across model generations. We provide evidence that this me…
- arXiv cs.AIagentsRetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
arXiv:2609.20784v2 Announce Type: replace-cross Abstract: Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to sup…
- arXiv cs.AIagentsQuantifying Overclaiming Propensity in Frontier LLM Agents
arXiv:2609.20812v3 Announce Type: replace-cross Abstract: Frontier coding agents are increasingly trusted to work autonomously for long periods of time, yet what they actually did is often hard to tell from their final r…
- arXiv cs.AIresearchERCPMP-Gx: Endoscopic Image and Video Dataset for Morphological, Histopathological, and Genomic Characterization of Colorectal Polyposis
arXiv:2609.20815v1 Announce Type: cross Abstract: Hereditary polyposis syndromes can be precursor lesions to colorectal cancer and are associated with a broad spectrum of extracolonic tumors. Early identification and acc…
- arXiv cs.AIresearchPaint-Anything: Unified Any-Color Control for Image Generation and Editing
arXiv:2609.20816v2 Announce Type: replace-cross Abstract: Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior…
- arXiv cs.AIresearchFAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
arXiv:2609.20817v1 Announce Type: cross Abstract: Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence. Most feed-forward meth…
- arXiv cs.AIresearchWorkspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision
arXiv:2609.20820v3 Announce Type: replace-cross Abstract: Complex robotic manipulation tasks frequently require a long-term memory of past events and actions. As conditioning on full histories renders policies prone to s…
- arXiv cs.AIagentsCoding Agents with Harness for Safe Robot Control
arXiv:2609.20822v2 Announce Type: replace-cross Abstract: Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way…
- arXiv cs.AIresearchoMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning
arXiv:2510.07731v4 Announce Type: replace Abstract: Organic reaction mechanisms describe the step-wise elementary processes by which reactants transform into intermediates and products, and are fundamental to understandi…
- arXiv cs.AIresearchTripScore: Aligning LLMs for Real-World Travel Planning via Expert-Calibrated Reward
arXiv:2510.09011v4 Announce Type: replace Abstract: In our deployed travel-planning service, most users give minimal inputs or free-form requests rather than the structured constraint checklists assumed by existing bench…
- arXiv cs.AIresearchBehavioral Coherence: A Method for Sensitive-Domain LLM Evaluation
arXiv:2512.13142v5 Announce Type: replace Abstract: People use LLMs for reproductive-health questions, including abortion-related support. A response can sound supportive while answers reinforce harmful assumptions: judg…
- arXiv cs.AIresearchModel Specific Task Similarity for Vision Language Model Selection via Layer Conductance
arXiv:2602.01346v2 Announce Type: replace Abstract: While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustiv…
- arXiv cs.AIagentsArchitectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM Performance
arXiv:2602.03128v2 Announce Type: replace Abstract: Multi-agent LLM frameworks are data-intensive systems that govern how agents orchestrate tasks, manage state, and coordinate decisions. These architectural choices cont…
- arXiv cs.AIresearchA Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities
arXiv:2603.02540v2 Announce Type: replace Abstract: Large language models (LLMs) display a unified "general factor" of capability across 10 benchmarks (a finding confirmed by our factor analysis of 156 models), yet they…
- arXiv cs.AIagentsReinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World Boundary
arXiv:2603.06813v3 Announce Type: replace Abstract: Ordinary decentralized multi-agent reinforcement learning presents each focal agent with a continual learning problem: peer updates change its induced rewards and dynam…
- arXiv cs.AIresearchGuideline-grounded retrieval-augmented generation for ophthalmic clinical decision support
arXiv:2603.21925v2 Announce Type: replace Abstract: In this work, we propose Oph-Guid-RAG, a multimodal visual RAG system for ophthalmology clinical question answering and decision support. We treat each guideline page a…
- arXiv cs.AIagentsSemantic Feature Analysis: Improving Agents Without Searching Over Rollouts
arXiv:2604.10513v2 Announce Type: replace Abstract: Ambiguity is an inherent property of natural-language agent specifications. When a system prompt leaves behaviour underdetermined, identical inputs follow divergent exe…
- arXiv cs.AIresearchSCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science
arXiv:2605.18630v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed as scientific AI as- sistants, and a growing body of benchmarks evaluates their capabilities across knowledge ret…
- arXiv cs.AIresearchMulti-Resolution Attribution from Adaptive Routing State
arXiv:2605.22866v2 Announce Type: replace Abstract: Adaptive hierarchical systems accumulate routing state as they learn which components to select. We show that this state already defines a coherent attribution over the…
- arXiv cs.AIresearchWhen Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis
arXiv:2606.29251v3 Announce Type: replace Abstract: Financial decision-makers face more information than they can directly inspect, making context compression necessary. Yet when large language models (LLMs) compress fin…
- arXiv cs.AIresearchAI Training Manager: Bounded Closed-Loop Control of Adaptive Training Recipes
arXiv:2606.29871v3 Announce Type: replace Abstract: We present the AI Training Manager, a bounded LLM-based metacognitive monitoring-and-control layer for machine-learning training. The Manager asynchronously observes st…
- arXiv cs.AIagentsFaithful, Not Corrective: Model Capability Governs Message-Format Effects in Multi-Hop Agent Relays
arXiv:2607.09678v2 Announce Type: replace Abstract: When LLM agents hand information to one another, does the message format matter? Two literatures disagree: format-optimization work reports that structured messages cut…
- arXiv cs.AIagentsWhen Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents
arXiv:2608.05810v2 Announce Type: replace Abstract: Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: past a critical p…
- arXiv cs.AIresearchFitAQA: A Benchmark of Fitness Action Quality Assessment for Multimodal Large Language Models
arXiv:2608.08736v2 Announce Type: replace Abstract: Fitness Action Quality Assessment (AQA) is important for intelligent sports training, yet the capabilities of Multimodal Large Language Models (MLLMs) in this setting r…
- arXiv cs.AIresearchAttributing Preprocessing Invariance in Spectral Foundation Models
arXiv:2608.14227v3 Announce Type: replace Abstract: A spectral foundation model should remain useful when laboratories preprocess spectra differently. The standard test trains a classifier under one pipeline and evaluate…