AI News

A Resilience-as-a-Service assessment framework for coordinated disruption response in interdependent urban transit systems (arxiv.org)

ZIPP:Zero-shot Image Personalization from Personas (arxiv.org)

Beyond Pass Rate: A Multilingual, Execution-Grounded Evaluation of Open Code LLMs (arxiv.org)

Constraint-Aware Optimization for Robust Protein Stability Prediction (arxiv.org)

ConSteer-RL: Steering Reasoning Capabilities in Large Language Models via Confidence-Aware Reinforcement Learning (arxiv.org)

DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination (arxiv.org)

Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense (arxiv.org)

When Behavioral Safety Evaluation Fails: A Representation-Level Perspective (arxiv.org)

Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Models (arxiv.org)

Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization (arxiv.org)

STAR: Rethinking MoE Routing as Structure-Aware Subspace Learning (arxiv.org)

Q-Delta: Beyond Key-Value Associative State Evolution (arxiv.org)

Semantic Quorum Assurance: Collective Certification for Non-Deterministic AI Infrastructure (arxiv.org)

Instrumental convergence and power-seeking (arxiv.org)

Noise-Adaptive High-Probability Regret Bounds for Online Convex Optimization (arxiv.org)

CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learning (arxiv.org)

Bridging Expert Knowledge and Automated Feature Engineering via Self-Evolution (arxiv.org)

RAILS: Verification-Native Clearing For Agentic Commerce (arxiv.org)

SafeECGMatch: Calibration-Aware Joint Frequency and Time Space Semi-Supervised Learning for Open-Set ECG Classification (arxiv.org)

Evaluating the Impact of Task Granularity on Catastrophic Forgetting in Continual Learning (arxiv.org)

Enhancing AI Interpretability and Safety through Localised Architectures (arxiv.org)

Overcoming the Limits of Finite Difference Method; Physics-Informed Neural Network for Noisy High-Dimensional Heat Diffusion (arxiv.org)

ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems (arxiv.org)

Structure-Conditioned Actor-Critic Branches for Quality-Diversity Reinforcement Learning (arxiv.org)

Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery (arxiv.org)

Minibatch Selection via Partition Matroid Constrained Gradient Matching (arxiv.org)

The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning (arxiv.org)

CAAL: Contextual Bandits based Online Hand-Craft Active Learning Strategy Selection (arxiv.org)

Layer-wise Derivative Controlled Networks Achieve Competitive Accuracy and Gradient Stability Across Data Regimes (arxiv.org)

InA-Probe: Instruction-Aware Active Probing for Time Series Forecasting with LLMs (arxiv.org)

Distilling LLM Reasoning into an Interpretable Policy Tree for Human-AI Collaboration (arxiv.org)

Quantitative Promise Theory: Intentionality and Inference in Autonomous Agents (arxiv.org)

PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR (arxiv.org)

AgentTrust: A Self-Improving Trust Layer for AI-Agent Actions (arxiv.org)

DN-Hypo-Pipeline: An AI-Driven Workflow for Hypothesis Generation via Large Language Models and Scientific Explanations (arxiv.org)

A Regret Minimization Framework on Preference Learning in Large Language Models (arxiv.org)

Temporal Coverage over Density: Parsimonious Training-Set Design for ML Climate Downscaling (arxiv.org)

Strained Coherence: A Pre-Failure Signal in Coding Agent Execution Trajectories (arxiv.org)

Breaking the Bubble: Asynchronous Pipeline Parallel Training with Bounded Weight Inconsistency (arxiv.org)

Still: Amortized KV Cache Compaction in a Single Forward Pass (arxiv.org)

Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual Saturation (arxiv.org)

Frequency-based Constrained Sampling for Interval Patterns (arxiv.org)

VESTA: A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents (arxiv.org)

Scaffold Effects on GAIA: A Controlled Comparison (arxiv.org)

Standpoint Logics with Defeasible Beliefs (arxiv.org)

Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets (arxiv.org)

Prescriptive Scaling Reveals the Evolution of Language Model Capabilities (arxiv.org)

On the Complexity of Offline Reinforcement Learning with $Q^\star$-Approximation and Partial Coverage (arxiv.org)

More Bang for the Buck: Improving the Inference of Large Language Models at a Fixed Budget using Reset and Discard (ReD) (arxiv.org)

Self-Supervised Dynamical System Representations for Physiological Time-Series (arxiv.org)