OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding Paper • 2610.18829 • Published 15 days ago • 751
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 28 days ago • 235
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It Paper • 2609.36585 • Published 29 days ago • 42
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 29 days ago • 208
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published Sep 1 • 522