AI News

Second Maximum of a Gaussian Random Field and Exact (t-)Spacing test (arxiv.org)

Provably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty Equivalents (arxiv.org)

The World Won't Wait: Evaluating and Teaching Agents Under a Live Clock (arxiv.org)

PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents (arxiv.org)

Learning from Unverified Peers via Shared Residual Distillation (arxiv.org)

When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models (arxiv.org)

Prism-1: Position- and Rival-Independent Scoring for System One Models (arxiv.org)

Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration (arxiv.org)

The Self-Improvement Problem (arxiv.org)

AgentPerturb: Evaluating LLM Agent Robustness under Controlled Interaction Perturbations (arxiv.org)

RoLaQ: Joint Rotation and Range Calibration for 2-Bit KV Caches in Multi-Head Latent Attention (arxiv.org)

Representation Redistribution in Sparse Autoencoders (arxiv.org)

Learning Intrinsic Dynamics in Latent World Models (arxiv.org)

Evaluating Inquiry Learning in LLM-Based Agents: Hypothesizing, Reasoning, and Exploration (arxiv.org)

LoopAhead: Speculating Ahead for Faster Decoding in Looped Language Models (arxiv.org)

LOADBench: A Large Open Analog Dataset and Benchmark for Machine Learning in IC Design (arxiv.org)

ClaimScope: Label-Blind Witness Verification for Mathematical Claim Auditing (arxiv.org)

Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond (arxiv.org)

Agent Status Protocol (ASP): A Lightweight Specification for State Reporting in Multi-Agent Systems (arxiv.org)

Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction (arxiv.org)

Learning from Interaction Experience via Localized Context Distillation (arxiv.org)

Do Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for Agents (arxiv.org)

From Perception to Prediction and Intervention: Benchmarking Proactive Video Assistants in Real-Life Scenarios (arxiv.org)

A Quantum Machine Learning Approach to Content-Based Media Recommendation (arxiv.org)

When Does Muon Actually Win? A Paired Data-, Time-, and Tuning-Budget Benchmark (arxiv.org)

Uncertainty Quantification in Pairwise Difference Learning for Classification (arxiv.org)

V-SHARE: Provable Convergence Guarantees for Advantage-based Algorithms (arxiv.org)

What Does History Add? Calendar Controls and Information-Timing Audits for University Trajectory Forecasting (arxiv.org)

Learning to Forecast on Multiple Spatiotemporal Hierarchies (arxiv.org)

Multi-Reward Hacking: From Aggregation-Induced Drift to Trust-Anchored Defense (arxiv.org)

Fault Detection and Bit-Error Rate Diagnostics in Optical Wireless Links Using Edge-AI (arxiv.org)

JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs (arxiv.org)

Constrained Multi-Agent Reinforcement Learning in Imagination (arxiv.org)

Money-Mule Detection as a Relational Learning Problem: A Study on the RBIH NFPC Dataset (arxiv.org)

Bias Control and Injection for Multi-Agent Aggregation (arxiv.org)

The Density of Thought: Predicting and Steering Reasoning in Large Language Models (arxiv.org)

Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL (arxiv.org)

Compatibility Matters: A Framework for Token-Level Teacher Selection in On-Policy Distillation (arxiv.org)

Not All Change Is Damage: Update-Matched Unlearning for Large Language Models (arxiv.org)

Learning and Forecasting Multiscale Spatiotemporal Epidemic Dynamics with Lagrangian-Eulerian Graph Neural ODEs (arxiv.org)

Hard Way, The Only Way: Provable Merits of Training on Hardest Examples (arxiv.org)

Mallea: Building, Steering, and Memorizing Worlds with Coding Agent (arxiv.org)

Diviner: Agentic RCA with Human-Governed Adaptation for Large-Scale Infrastructure (arxiv.org)

Auditing Escalation Reliability in Healthcare LLM Agents: A Perturbation-Controlled Benchmark of Workflow-State Failures (arxiv.org)

AutoOnboarder: Autonomously Onboarding LLM Agents (arxiv.org)

Rubric Judgments Lack Uncertainty: Conformal Weighting for LLM Evaluation (arxiv.org)

Poisoning the corpora of protein design systems during pre-training and retrieval (arxiv.org)

INCONVENIENT: A Benchmark to Assess LLM Generalization Capabilities from Convenience Samples (arxiv.org)

CausalEvo: Causal Skill Self-Evolution for Health LLM Agents (arxiv.org)

Imperfect Is Perfect: Learned Column Prefilling for Branch-Price-and-Cut (arxiv.org)