False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 19 days ago • 665
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 20 days ago • 565
CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers? Paper • 2610.07557 • Published 13 days ago • 76
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published Sep 15 • 865