AI News

CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems (arxiv.org)

LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information (arxiv.org)

JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models (arxiv.org)

FedHisto-PAST: Parameter-Efficient Stain-Aware Federated Learning for Cross-Site Lung Histopathology Classification (arxiv.org)

Teacher-Anchored Selection of Post-Training Quantized Models under Domain Shift (arxiv.org)

The Price of Thought: Does Test-Time Reasoning Pay in LLM Trading? (arxiv.org)

ReG-SAM: Reference Graph-Driven SAM for 2D Foundational Vessel Segmentation (arxiv.org)

LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents (arxiv.org)

Audio LLMs Know When They Can't Hear You (arxiv.org)

Spectral Feedback for Test-Time Alignment of Protein Diffusion Models (arxiv.org)

A Synthetic Ground-Truth Framework for the Evaluation of Explainable AI Methods (arxiv.org)

Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems (arxiv.org)

Improving Visual Sensitivity of LLMs on Multimodal Machine Translation with Metric-based Loss Weighting (arxiv.org)

Bridging LLM Agents and Data Spaces: An Architectural Mediation Approach using the Model Context Protocol (arxiv.org)

Rethinking Data Quality for AI-Driven Systems: Evidence from Practitioner Interviews (arxiv.org)

Acoustic-to-Text KV Compression for Full-Duplex Speech Models (arxiv.org)

HuPER: A Human-Inspired Framework for Phonetic Perception (arxiv.org)

When Is a Multi-Agent Code Judge Actually Grounded? Two Label-Free Measurements, and a Judge That Declines to Guess (arxiv.org)

ScopeBench: Do Agents Preserve Engagement Boundaries Under Goal Pressure? (arxiv.org)

Bringing AI to Autonomous Systems -- From Cognition to Collective Intelligence (arxiv.org)

T-RoPE: Time-Aware Rotary Position Embedding for Sequential Recommendation (arxiv.org)

Backbone-Adaptive Evidence Routing for Robust Pairwise LLM Judging (arxiv.org)

Beyond Bag-of-Words: Diagnosing Compositional Binding Failures in Vision-Language Models (arxiv.org)

Geometric Inconsistency Localization in Multi-View Image Sets (arxiv.org)

AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents (arxiv.org)

RAPTOR: Ridge-Adaptive Logistic Probes (arxiv.org)

Dynamic Welfare-Maximizing Pooled Testing (arxiv.org)

Prompt-Based Continual Compositional Zero-Shot Learning (arxiv.org)

CG-HAF: An Interpretable Global-Local Lesion-Burden Fusion Framework for Ordinal Acne Severity Grading in Agentic Skincare Support (arxiv.org)

Thinking Less to Simulate Better: Intuitive Prompting Improves LLM Agents Simulating Individual Social Media Reactions, Including Unfamiliar Content (arxiv.org)

Rank-Reliable Teacher-Guided Fitness Approximation for Expensive Evolutionary Optimization: A TinyML Architecture Search Study (arxiv.org)

DyMD: Preserving Interaction Dynamics through Distribution Matching Distillation in Few-Step Video World Models (arxiv.org)

Predicting Transmembrane Protein Topology from 3D Structure (arxiv.org)

Towards VLA-Dreamer: Refining VLA Behavior Using World Models (arxiv.org)

Statistical attribute alignment for black-box generative AI via output post-processing (arxiv.org)

Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer (arxiv.org)

A Safety-Bounded SDC-to-MCP Gateway for Medical AI Agents (arxiv.org)

UniAR: A Unified Framework for Autism Recognition Enhanced by Multi-View Prompt Learning (arxiv.org)

Softmax Reparameterization for Output-Head Quantization (arxiv.org)

Resource-Optimized and Energy-Aware Agentic AI Framework Anchored on Blockchain for Secure Software Supply Chains (arxiv.org)

Cognitive Skills in the Age of AI: Computing Students and Experts Perceptions (arxiv.org)

Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding (arxiv.org)

Guiding End-to-End Driving Models with Endpoint-Constrained Trajectory Optimization (arxiv.org)

MoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries (arxiv.org)

Externalized CPDAG Summaries Improve LLM Causal Deduction (arxiv.org)

Combining General and Domain-Specific Pretext Tasks for Brain MR Image Segmentation (arxiv.org)

VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control (arxiv.org)

Threat-Aware Energy-Efficient Deployment for Dynamic UAV Networks: A Multi-Agent RL Approach (arxiv.org)

A Framework for Identifying, Categorizing, and Explaining Bias in AI-Generated Code (arxiv.org)

Subjects, Not Authors: The Authorship Hazard in Agentic Dataspaces (arxiv.org)