False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 6 days ago • 584
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement Paper • 2609.38721 • Published 6 days ago • 291
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 7 days ago • 577
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published 21 days ago • 815
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience Paper • 2609.03241 • Published Sep 3 • 54