01. Quantifying Overclaiming Propensity in Frontier LLM Agents

87% worth reading · novelty 1.8/3 · benchmark/eval · cs.AI

02. Chronicle: Cut-Point Replay for Regression Testing of LLM Agents

84% worth reading · novelty 1.9/3 · new method · cs.CL

03. Semantic Action Graph: A Shared Representation for Agent Grounding and Human Interpretation of Sports Highlights

82% worth reading · novelty 1.8/3 · new method · cs.AI

04. Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL

80% worth reading · novelty 1.7/3 · new method · cs.CL

05. Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation

81% worth reading · novelty 1.7/3 · new method · cs.AI

06. RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

83% worth reading · novelty 1.5/3 · new method · cs.AI

07. RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents

79% worth reading · novelty 1.7/3 · new method · cs.AI

08. Large Language Models as Falsifiers for Cyber-Physical Systems

75% worth reading · novelty 1.9/3 · new method · cs.AI

09. An Empirical Study of Harness Design for Coding Agents

85% worth reading · novelty 1.2/3 · benchmark/eval · cs.AI

10. On-Demand Attention: Language Models Know When to Recall

70% worth reading · novelty 1.7/3 · new method · cs.CL

11. Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation

70% worth reading · novelty 1.7/3 · new method · cs.AI

12. Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure

62% worth reading · novelty 1.7/3 · new method · cs.AI

13. HerHealthEval: Evaluating Multilingual and Register-Sensitive Understanding of Women's Health Communication

58% worth reading · novelty 1.9/3 · benchmark/eval · cs.CL

14. Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision

56% worth reading · novelty 1.7/3 · new method · cs.AI

15. PAA: The Probabilistic Allen Algebra: A Generative and Complete Probabilistic Extension of Allen's Interval Relations

49% worth reading · novelty 2.0/3 · new method · cs.CL

16. Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations

48% worth reading · novelty 2.0/3 · benchmark/eval · cs.AI

17. Score Centering Stabilizes Off-policy Reinforcement Learning

49% worth reading · novelty 1.9/3 · new method · cs.LG

18. GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies

46% worth reading · novelty 1.8/3 · new method · cs.AI

19. Summarization Bias: The Directional Collapse of Objective Projection into Told-Mode Labels in Large Language Models --- A Conceptual Framework and Registered Test Protocol

42% worth reading · novelty 1.9/3 · survey/position · cs.CL

20. Unifying Models of Intergroup Hostility in Online Discourse

42% worth reading · novelty 1.9/3 · new method · cs.CL