AI News

Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents (arxiv.org)

Warrant Theory (arxiv.org)

Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens (arxiv.org)

RetroThinker: Enabling Retrospective Thinking in Speech LLMs (arxiv.org)

Understanding Operator Attitudes Toward AI-Supported Decision Making in Maritime Operations (arxiv.org)

Continuous-Time Acoustic Modelling with Neural Controlled Differential Equations (arxiv.org)

Physics-Informed Neural Networks to Infer the Perpendicular Energy Conductivity in the Scrape-Off Layer of Stellarator Devices (arxiv.org)

A Comparative Evaluation of Pre-trained Convolutional Neural Networks for Melanoma Detection (arxiv.org)

Cross-Lingual Clinical Annotation Projection as Constrained Text Generation: A Six-Language Study (arxiv.org)

Grounding Agent Memory: Environment-Probing Curation for Enterprise Agents (arxiv.org)

Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning (arxiv.org)

MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG (arxiv.org)

Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation (arxiv.org)

KuaiRP Series Role-playing Models Technical Report (arxiv.org)

Same Day, Same Story; One Day Ahead, a Different Signal: The Dual Validity of Financial Sentiment (arxiv.org)

Autonomous Chemical Mechanistic Discovery through Agentic Reasoning and Validation (arxiv.org)

DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat (arxiv.org)

SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution Semantics (arxiv.org)

Can LLMs Follow Medical Expert Logic? A Benchmark for Hierarchical Logical Consistency in Risk-of-Bias Assessment (arxiv.org)

Agentic Share-of-Search: A Multi-Agent AI System for Competitive Decision-Making in LLM-Mediated E-Commerce (arxiv.org)

An AI-Powered Culturally Aware Chatbot for Stress Detection and Wellness Support among Pakistani University Students Using NLP and Machine Learning (arxiv.org)

A Voice-Interactive Multi-Agent System for Smart Operating Rooms: Architecture Design and Key Technologies (arxiv.org)

NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment (arxiv.org)

Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents (arxiv.org)

AI-Powered Flare Combustion Efficiency Estimation (arxiv.org)

Lightweight LiDAR-Based Cone Detection Framework Using Random Forest for Formula Student Driverless (arxiv.org)

Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks (arxiv.org)

From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models (arxiv.org)

2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation (arxiv.org)

GRIPNet: Gaussian Radial Intensity Prior Guided Architecture for Pulmonary Nodule Detection in CT (arxiv.org)

Cognitive Digital Twins: Ethical Risks and Governance for AI Systems That Model the Mind (arxiv.org)

SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models (arxiv.org)

Learning to Think Like a Cartoon Captionist: Incongruity-Resolution Supervision for Multimodal Humor Understanding (arxiv.org)

Beyond Prompting: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration (LOGIC) (arxiv.org)

Towards AI-Driven Policing: Interdisciplinary Knowledge Discovery from Police Body-Worn Camera Footage (arxiv.org)

GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay (arxiv.org)

The Semantic Elevation Operator and the Closure of the Undecidable Class under Preservation (arxiv.org)

On the Impact of Anonymization on the Performance of Large Language Models (arxiv.org)

On the Regularization Landscape for the Linear Recommendation Models (arxiv.org)

Can Edge-Deployable Vision-Language Models Identify Species? (arxiv.org)

The Convention Gap: Towards Measuring Implicit Communication in Cooperative AI Evaluation (arxiv.org)

From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge (arxiv.org)

When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making (arxiv.org)

(Whose defaults?) Is artificial intelligence reorienting archaeological methods? (arxiv.org)

MindTopo: Can Foundation Models Reason in Topological Space? (arxiv.org)

Artificial Id: Drive and Persistent Alignment in Agentic AI (arxiv.org)

X-RACE: XAI-assisted Recurrent neural network Attribution for Channel Estimation (arxiv.org)

Probabilistic Focal Search: Accelerating Bounded-Suboptimal Search via Lower-Bound Advancement (arxiv.org)

AI Soccer Analyst: Stage-Aware and Verifiable Human-AI Collaboration for Soccer Data Analysis (arxiv.org)

Does Linguistic Structure Enrichment Enhance Coherence Assessment? Not With Current Architectures (arxiv.org)