AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsPhysAI-Bench: A Benchmark for LLM-Based Agentic Decision-Making in Autonomous UAV-Centric Physical AI
arXiv:2609.23695v1 Announce Type: new Abstract: Recent advances in Physical AI have accelerated the use of foundation models in autonomous systems such as unmanned aerial vehicles (UAVs), which must perceive, reason, pla…
- arXiv cs.AIagentsScholarStack: Layered Research Asset Orchestration and Cross-Task Reuse for Scientific Agents
arXiv:2609.23735v3 Announce Type: replace Abstract: Scientific agents support a range of literature-based research tasks, such as retrieval, question answering, evidence-grounded generation, and claim assessment. Most ex…
- arXiv cs.AIresearchOn Probabilistic Inference Through Parametric Tensor Decomposition in Base Tensor Networks
arXiv:2609.23774v1 Announce Type: new Abstract: Probabilistic inference is generally only tractable in low-treewidth graphical models, limiting its effective applicability in high-treewidth settings. Many existing method…
- arXiv cs.AIagentsTotal Cost of Agency: Exact Attribution of Memory Injection Cost in Multi-Agent LLM Workflows
arXiv:2609.23790v1 Announce Type: new Abstract: Every node in a multi-agent large language model (LLM) workflow retrieves context from memory and injects it into its prompt, where those injected tokens are billed as inpu…
- arXiv cs.AIagentsWorkWorlds: An Infrastructure for Evaluating AI Agents on Workplace Tasks
arXiv:2609.23806v2 Announce Type: replace Abstract: Many knowledge-work benchmarks are constructed around individual tasks, with the context needed for each task selected together with or after the task has been specifie…
- arXiv cs.AIresearchPretraining of Medical Visual Encoders Toward Multi-modal Large Language Models
arXiv:2609.23860v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) commonly reuse visual encoders pretrained with CLIP, although the features of these ViTs are ultimately consumed by autoregressive…
- arXiv cs.AIresearchExplainable Recommendations at Scale: LLM Rationales for YouTube Music Artist Discovery
arXiv:2609.23877v1 Announce Type: new Abstract: Modern music streaming platforms face a persistent tradeoff: exploiting familiar content versus driving the exploration of novel items. While users frequently desire discov…
- arXiv cs.AIresearchIncreasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer
arXiv:2609.23917v1 Announce Type: new Abstract: Chess involves complex reasoning in a deterministic environment, which makes it a useful setting for studying the mechanisms of computation inside transformers. The Maia-3…
- arXiv cs.AIresearchEcho State Network (ESN) for Signal Recovery in RF-Impaired IBFD MIMO Systems
arXiv:2609.23945v1 Announce Type: new Abstract: In-band full-duplex (IBFD) multiple-input multiple-output (MIMO) systems enable simultaneous transmission and reception on the same frequency band, improving spectral effic…
- arXiv cs.AIagentsAgents That Edit Documents: Measuring Agentic PDF Forgery Against a Non-Agentic Control
arXiv:2609.23953v2 Announce Type: replace Abstract: AI agents that carry a multi-step computer task through on their own became ordinary tools in the past year, and the same autonomy is available to anyone whose task is…
- arXiv cs.AIagentsDivergent strategies and convergent outcomes in autonomous materials discovery
arXiv:2609.23957v1 Announce Type: new Abstract: Scientific agents are mostly evaluated on whether they complete tasks or recover known results; we instead study variation across repeated open-ended campaigns. Sixteen sep…
- arXiv cs.AIagentsUniK: Universal Knowledge Perception for Digital and Physical AI
arXiv:2609.23971v1 Announce Type: new Abstract: Two transformative classes of AI systems are reshaping how organizations operate: \textit{digital AI}, which reasons over enterprise knowledge to power chatbots and agent w…
- arXiv cs.AIagentsLEAP-NBV: Lightweight Edge Active-Perception for Foundation-Model Next-Best-View Planning
arXiv:2609.23974v1 Announce Type: new Abstract: Foundation models are endowing autonomous systems with greater intelligence, enabling a more comprehensive understanding of the environment through visual perception. A rep…
- arXiv cs.AIagentsJev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
arXiv:2609.23986v1 Announce Type: new Abstract: Agentic memory is becoming essential for long-horizon AI agents, yet many existing systems rely on autoregressive LLMs to control how memories are organized, retrieved, and…
- arXiv cs.AIagentsACLArena: Agent Continue Learning in Multi-stage Post-training
arXiv:2609.23989v1 Announce Type: new Abstract: Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically acquired at a distinct stage of training. Yet there is…
- arXiv cs.AIagentsFinInteract: Benchmarking Clarification and Intent Integration in Ambiguous Financial Question Answering
arXiv:2609.24002v1 Announce Type: new Abstract: Large language model agents increasingly answer financial questions by searching regulatory filings. Such questions are often deceptively under-specified: Meta Platforms' "…
- arXiv cs.AIresearchTesting, not presuming, adequacy: calibrating generative social simulators against emergent network structure
arXiv:2609.24012v2 Announce Type: replace Abstract: Validation of generative social simulators often stops at face validity: emergent network structure is compared descriptively, without quantified parameter uncertainty…
- arXiv cs.AIresearchContext-Aware Pre-Deployment Evaluation of AI Systems: A Regulatory Framework for Nigerian Fintech
arXiv:2609.24016v1 Announce Type: new Abstract: Commercial large language models are increasingly deployed across African fintech infrastructure for fraud detection and customer communication, yet no Nigerian or African…
- arXiv cs.AIresearchSynthesizing Reactive Character Behaviors for Continuous Games via Programmatic Policy Search
arXiv:2609.24025v1 Announce Type: new Abstract: We present a method for synthesizing reactive character behaviors for continuous games as compact, human-readable programs. Game AI practice still relies heavily on manuall…
- arXiv cs.AIagentsStructured Decomposition for Reliable LLM-Generated Access Control Policies
arXiv:2609.24036v1 Announce Type: new Abstract: This paper presents an LLM-based system that translates natural-language access control policies (NLACPs) into executable Rego code for Open Policy Agent (OPA). It provides…
- arXiv cs.AIresearchRepresentation-guided in-context learning for medical image interpretation with multimodal large language models
arXiv:2609.24057v1 Announce Type: new Abstract: Medical image interpretation is central to diagnosis and care, yet adapting general-purpose multimodal large language models (MLLMs) often requires resource-intensive domai…
- arXiv cs.AIagentsIncremental Consistency Execution for Autonomous Intelligent Systems
arXiv:2609.24090v1 Announce Type: new Abstract: Long-horizon autonomous intelligent systems rely on heterogeneous components such as large language models, databases, external APIs, and rule engines, while their external…
- arXiv cs.AIresearchDocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documents
arXiv:2609.24092v1 Announce Type: new Abstract: Real-world document processing systems rely on rigid, predefined schemas, yet critical target fields often lack direct visual counterparts on the page. Extracting these imp…
- arXiv cs.AIresearchWhen More Evidence Hurts: Publication-Bias Drift and Principled Stopping for Biomedical Causal Search
arXiv:2609.24101v1 Announce Type: new Abstract: Automated biomedical evidence synthesis depends on retrieving published studies, but the biomedical literature is systematically skewed toward positive findings. Deeper ret…
- arXiv cs.AIagentsEDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation
arXiv:2609.24115v1 Announce Type: new Abstract: Tool-calling LLM agents are increasingly deployed in enterprise applications. However, effective evaluation and optimization require high-quality, diverse task datasets tha…
- arXiv cs.AIagentsSelf-Healing Harness for Runtime Oversight of Agent Self-Modification
arXiv:2609.24130v1 Announce Type: new Abstract: LLM agents can change their own future behavior, raising a basic control question of which self-generated changes should be allowed to persist. We formulate this as admissi…
- arXiv cs.AIagentsAPEXA: Execution-Integrity Enforcement for Multi-Agent LLM Automation of Synchrotron Data Reduction
arXiv:2609.24165v2 Announce Type: replace Abstract: LLM agents can make expert scientific workflows accessible through natural language, but a plausible response does not establish that the requested computation ran. Thi…
- arXiv cs.AIagentsCREDO: Variance-Guided Rubric Evolution for Replay-Corrected Credit Assignment
arXiv:2609.24174v1 Announce Type: new Abstract: Long-horizon language agents receive sparse terminal feedback, while intermediate rubrics provide structured but potentially misspecified assessments of progress. In resett…
- arXiv cs.AIresearchLIMIT: Less Is More for Instruction Tuning in Text-to-SQL
arXiv:2609.24186v1 Announce Type: new Abstract: Large language models have achieved remarkable progress on Text-to-SQL through reasoning-enhanced fine-tuning, yet existing approaches predominantly rely on massive instruc…
- arXiv cs.AIresearchSKstars at SHROOM: Visions Agreement-Guided Ensembling of Zero-Shot and LoRA-Adapted Vision--Language Models
arXiv:2609.24198v1 Announce Type: new Abstract: This paper describes the SKstars submission to SHROOM-Visions 2026, a shared task on fine-grained hallucination detection in large vision-language model outputs. The task r…
- arXiv cs.AIresearchRecovering Lost Details: Multi-Scale Frequency Compensation for Long-Term Time Series Forecasting
arXiv:2609.24229v1 Announce Type: new Abstract: Long-term time series forecasting has made significant progress by leveraging multi-scale information to capture hierarchical temporal patterns and model long-range depende…
- arXiv cs.AIresearchTaming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement
arXiv:2609.24243v3 Announce Type: replace Abstract: Reinforcement learning (RL) has substantially improved the reasoning capabilities of vision-language models (VLMs), yet it can induce chain-of-thought (CoT) obfuscation…
- arXiv cs.AIresearchUnsupervised Brain Anomaly Detection as a Bayesian Inverse Problem with Diffusion Prior
arXiv:2609.24265v1 Announce Type: new Abstract: Unsupervised anomaly detection (UAD) aims to localize abnormal regions in medical scans without pixel-level annotations. A typical strategy seeks to reconstruct a pseudo-he…
- arXiv cs.AIagentsHow Many Pixels Is a Digit Worth? Place-Aware Coordinate Entropy for GUI Agent Confidence Estimation
arXiv:2609.24277v1 Announce Type: new Abstract: GUI agents predict click coordinates as digit-token sequences, but standard text-LLM confidence estimation methods rank correct clicks from wrong ones only weakly. GUI-spec…
- arXiv cs.AIagentsWhen and How Should an Agent Clarify? CIGAsk: Teaching LLMs to Clarify via Counterfactual Information Gain
arXiv:2609.24290v1 Announce Type: new Abstract: Instruction-tuned LLMs faced with underspecified queries often commit to a single interpretation rather than ask for clarification, producing confidently wrong answers. In…
- arXiv cs.AIresearchBrain-Token Learning: Microstate-Based Tokenization and Multi-Scale Interaction for Long-Horizon EEG Sequence Modeling
arXiv:2609.24324v1 Announce Type: new Abstract: Electroencephalography (EEG) provides a non-invasive window into dynamic brain activity, yet modeling long-horizon EEG sequences remains challenging due to their high tempo…
- arXiv cs.AIresearchLADDER: Graph-Guided Diffusion Language Models for Efficient Multi-Hop Reasoning
arXiv:2609.24346v1 Announce Type: new Abstract: Graph Retrieval-Augmented Generation (GraphRAG) has remarkably enhanced large language models on complex reasoning by leveraging structured entity topologies. However, exis…
- arXiv cs.AIagentsFew-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs
arXiv:2609.24352v1 Announce Type: new Abstract: Large language models (LLMs), when acting as agents, are expected to take observed data in context, infer the latent state space underlying the world, and leverage it for d…
- arXiv cs.AIagentsVLM-in-Sandbox: Visual Workspaces for Agentic Visual Reasoning
arXiv:2609.24362v1 Announce Type: new Abstract: Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language models to vision-langu…
- arXiv cs.AIresearchPredicting Postprandial Glycemic Response from Meal Images, Clinical Variables, and Gut Microbiome Information
arXiv:2609.24453v1 Announce Type: new Abstract: Predicting postprandial glycemic response (PPGR) is fundamental to personalized nutrition and type 2 diabetes management, yet existing approaches typically rely on manually…
- arXiv cs.AIresearchFathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards
arXiv:2609.24480v1 Announce Type: new Abstract: Deploying Large Language Models (LLMs) in healthcare requires robust performance across two complementary dimensions - diagnostic reasoning: the convergent, evidence-driven…
- arXiv cs.AIresearchNot All Task Vectors Need Equal Rank: Energy-Proportional Allocation for Model Merging
arXiv:2609.24517v1 Announce Type: new Abstract: Model merging aims to combine multiple fine-tuned models derived from a common pretrained model into a single multi-task model without additional joint training. Recent spe…
- arXiv cs.AIresearchThe Endless Exam: Mathematical Constructions from Today's Models toward Superintelligence
arXiv:2609.24555v2 Announce Type: replace Abstract: We introduce the Endless Exam, a benchmark spanning fourteen parameterised families of mathematical construction problems, with verifiable scores that distinguish progr…
- arXiv cs.AIagentsAscent: An Agentic System over the Model Context Protocol for Real-World Clinical Data Analysis
arXiv:2609.24620v1 Announce Type: new Abstract: Answering epidemiological questions from real-world clinical data requires medical coding, schema-aware SQL, and validation of implicit choices about populations, denominat…
- arXiv cs.AIresearchCustom Named Entity Recognition and Topic Classification for Global Health Publications
arXiv:2609.24625v1 Announce Type: new Abstract: How should natural language processing models be selected and adapted for global health literature in environments where annotated data and computational resources are limi…
- arXiv cs.AIagentsDUMA-Bench: A Dual-Control Multi-Agent Benchmark for Evaluating LLM Agent Security
arXiv:2609.24662v1 Announce Type: new Abstract: LLM-based agents increasingly operate in environments where they interact with users, tools, and external systems. Yet most security evaluations assume passive users and st…
- arXiv cs.AIagentsBeyond Endpoint Performance: Process-Level Evaluation of Self-Evolving Agents
arXiv:2609.24663v1 Announce Type: new Abstract: Self-evolving agents convert interaction feedback into persistent artifacts, such as memories or skills, which in turn guide subsequent decisions. As these artifacts are it…
- arXiv cs.AIresearchTimeLitmus: A Diagnostic Benchmark for Cross-Modal Understanding and Explanation Faithfulness in Event-Conditioned Time-Series Prediction
arXiv:2609.24677v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to make predictions from numerical time-series histories and textual events. Yet accuracy alone cannot reveal whether cor…
- arXiv cs.AIagentsWorld State Generator
arXiv:2609.24744v1 Announce Type: new Abstract: Language agents solve complex tasks through plans and actions. A single step the world refuses puts the goal out of reach, and what the agent does next decides the task. Pr…
- arXiv cs.AIagentsEpi-Logic: A Conceptual Framework for Epistemic Runtime Control, Schema Validity Checking, and Controlled Accommodation in Autonomous AI Agents
arXiv:2609.24755v1 Announce Type: new Abstract: Autonomous AI agents are increasingly deployed in areas where wrong decisions are hard to reverse. This paper examines schema mismatch: the condition in which an agent oper…