AI News

Agentic Hazard Mapper: Emulating Expert Map-Making with AI Agents for Risk Communication (arxiv.org)

What Open-Source Projects Tell Their Coding Agents: A Census of AGENTS.md and CLAUDE.md (arxiv.org)

Anti-coherence Regularized Absolute Scaling for Out-of-Distribution Detection (arxiv.org)

Generalized green and red concepts for artificial intelligence, big data, and information and communication technologies: Multidimensional framework and countermeasures (arxiv.org)

PrefO2O: Zero-Shot Preference-Based Reinforcement Learning via Offline-to-Online Latent Preference Transfer (arxiv.org)

Rethinking Multi-View Fusion for Urban Representation Learning (arxiv.org)

What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design (arxiv.org)

AgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents (arxiv.org)

Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution (arxiv.org)

Learning from Next-Frame Prediction: Towards Unified and Scalable Visual World Modeling (arxiv.org)

ImageRSI: Verification-Driven Recursive Self-Improvement for Agentic Image Generation (arxiv.org)

A Foundation Model for Policy In-Context Longitudinal Causal Effect Estimation (arxiv.org)

SWE-Clar: Can Coding Agents Clarify Incomplete Client Requirements and Deliver Greenfield Software? (arxiv.org)

Machine-Readable Operator Manuals over the ISO 11783 Network for Offline, Multilingual LLM Assistance (arxiv.org)

FOCUS: A Lightweight Mamba-2 Model for EEG-Based Cognitive Workload Classification (arxiv.org)

Adaptive Control of Scientific Instruments with Nonstationary Responses through Multimodal Agents (arxiv.org)

MusicTwins: Training Audio-Language Models to Listen like Their Persona (arxiv.org)

Rethinking Structured Generation: Can Graph-Based Reasoning Resolve Ambiguity? (arxiv.org)

Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own Discoveries Are Statistical (arxiv.org)

FSVL: Taxonomic Fast-Slow Vision-to-Language Collaborative Framework for Interpretable Confusable Fish Species Identification and Knowledge Generation in the Middle Yangtze River (arxiv.org)

Knowing When to Stop: The Evidence-Action Gap in Coding Agents (arxiv.org)

Distributional Alignment of LLMs and Its Generalization Properties (arxiv.org)

NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding (arxiv.org)

Do VLAs Know They Will Fail? Interpretable Success and Failure Patterns in Physical AI Systems (arxiv.org)

Validating the Comparison, Not Just the Scorer: Why Overall Accuracy Can Mislead in Interactive LLM Evaluation (arxiv.org)

Towards robust long-context understanding of large language model via active recap learning (arxiv.org)

TGR-EvoDAG: A DAG-based Multi-Agent Code Evolution Framework for Generative Recommendation on Tencent (arxiv.org)

LLaCO: Continuous Diffusion for Large Language Models with Competition-Aware Semantic Scheduling (arxiv.org)

PAIR-SAFE: A Paired-Agent Approach for Runtime Auditing and Refining AI-Mediated Mental Health Support (arxiv.org)

CASE: Confusion-Aware Skill Evolution for Frozen Multimodal Emotion Models (arxiv.org)

Advancing SVD-based LLM Compression via Layer-Wise Error Model Search (arxiv.org)

Agentic AI Defense: Decode-Time Provenance Binding for MCP (arxiv.org)

Analysing Austrian Parliamentary Speeches by Predicting Party Affiliations (arxiv.org)

What the Query Remembers: Query Abstraction Governs Lexical and Dense Retrieval of Classical Arabic Poetry (arxiv.org)

Beyond Channel Data: Configuration-Enriched Radio Foundation Models (arxiv.org)

GeoDiv KAN Solver for Time Fractional Navier Stokes Equations on Complex Domains to Realistic CFD Reconstruction (arxiv.org)

Collaborative In-Context Learning for Indoor Radio Map Estimation (arxiv.org)

Complementing DINO Features with Image Structure for Part Discovery (arxiv.org)

HarnessMM: Recursive Self-Improvement for Harness Token Efficiency (arxiv.org)

DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks (arxiv.org)

When to Stop Penalizing Actions? Martingale GRPO for VLA Reinforcement Learning (arxiv.org)

IGG: A Benchmark for Interactive GUI Grounding under Visibility Constraints (arxiv.org)

LGMT: A Tool for Testing the Logical Reasoning Reliability of LLMs (arxiv.org)

Beyond Gain: Measuring Skill Internalization for Agent Skill Retirement (arxiv.org)

Beyond Post-Hoc Rewards: Privileged Reasoning Exploration for Multimodal Embeddings (arxiv.org)

POSEIDON: Scaling Training Environments for Scientific Agents from Code Repositories (arxiv.org)

Understanding Communication Failures in Multi-Agent LLM Systems (arxiv.org)

Astro2Method: Benchmarking LLMs on Machine Learning Method Selection in Astronomy (arxiv.org)

Mitigating the Likelihood Paradox in Flow-based OOD Detection: An Entropic Perspective (arxiv.org)

DealsFlow: An Evidence-Gated Agentic Harness for Venture Capital Deal Triage (arxiv.org)