AI News

OPD+: Rethinking the Advantage Design for On-Policy Distillation (arxiv.org)

Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning (arxiv.org)

Interaction-Limited Safe Continuous-Time RL for Dynamical Medical Treatment (arxiv.org)

Repair Before Veto: Repair-Augmented Constraint Learning for Contextual Decisions (arxiv.org)

Coordination Graphs for Constrained Multi-Agent Reinforcement Learning (arxiv.org)

SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training (arxiv.org)

MOC: Multi-Order Communication in LLM-based Multi-Agent Systems (arxiv.org)

Improving Hospital Process Management through Process Mining: A Case Study on COVID-19 Clinical Pathways (arxiv.org)

Non-Vacuous Certification of Transport MCMC via Oscillation-Controlled Normalizing Flows (arxiv.org)

ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning Tasks (arxiv.org)

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback (arxiv.org)

MViewRouter: Internalizing Geometric Equivariance via Multi-view Alternating Attention for Combinatorial Routing (arxiv.org)

PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder (arxiv.org)

COMAP: Co-Evolving World Models and Agent Policies for LLM Agents (arxiv.org)

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses (arxiv.org)

Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models (arxiv.org)

A Mathematical Conflict Framework for Contextual Data Modulation (arxiv.org)

AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design (arxiv.org)

A Fiber Criterion for Representation Identifiability in Supervised Learning (arxiv.org)

Soft-NBCE: Entropy-Weighted Chunk Fusion for Long-Context (arxiv.org)

LeAP: Learnable Adaptive Permutation for Feature Selection in Heterogeneous and Sparse Recommender Systems (arxiv.org)

HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces (arxiv.org)

A Per-Component Diagnostic Protocol for Neural HJB-PIDE Solvers under Control-Dependent L\'evy Jumps (arxiv.org)

From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning (arxiv.org)

Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization (arxiv.org)

HLL: Can Agents Cross Humanity's Last Line of Verification? (arxiv.org)

Beyond One-shot: AI Agents for Learning in Field Experiments (arxiv.org)

AGENTCL: Toward Rigorous Evaluation of Continual Learning in Language Agents (arxiv.org)

MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation (arxiv.org)

Accuracy, Stability, and Repeated-Run Reliability of Large Language Models on Deterministic Programming Tasks (arxiv.org)

Conditioned free-energy density of proteins using unbalanced solutions to constraint satisfaction problems (arxiv.org)

CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards (arxiv.org)

FreqLite: A Lightweight Frequency-Decomposed Linear Model with Adaptive Reversible Normalization for Robust Long-Term Time-Series Forecasting (arxiv.org)

SENSE: Semantic Embedding Navigation with Soft-gated Evaluation for Retrieval-based Speculative Decoding (arxiv.org)

All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learning (arxiv.org)

lmfaoooo at SemEval-2026 Task 1: Humor Is an Audience. Preference Modeling for Constrained Humor Generation (arxiv.org)

TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models (arxiv.org)

A Multi-Domain Red Teaming Framework for Safety, Robustness, and Fairness Evaluation of Medical Large Language Models (arxiv.org)

TCAR-Gen: Temporal Graph Retrieval with Evidence Fusion for Knowledge-Grounded Generation (arxiv.org)

Measuring and Mitigating Bias in Code Generated by Large Language Models (arxiv.org)

From Performance to Viability: A Bootstrap Framework for Latent-Space Representation Learning in Adaptive Biological Systems (arxiv.org)

Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning (arxiv.org)

Efficient Exploration for Iterative Nash Preference Optimization (arxiv.org)

Neural Network Compression by Approximate Differential Equivalence (arxiv.org)

ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts (arxiv.org)

Business Utility of Large Language Models as Exploratory Data Analysis Agents (arxiv.org)

LLMs for Cardiovascular Risk Prediction from Structured Clinical Data (arxiv.org)

Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing (arxiv.org)

Update Opacity: Epistemic Accessibility and Governance Under AI System Change (arxiv.org)

Beyond Tool Adoption: A Practical Five-Stage Developmental Continuum for AI Literacy in Higher Education (arxiv.org)