The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 12 days ago • 552
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 11 days ago • 569
GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis Paper • 2609.38923 • Published 11 days ago • 123
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 13 days ago • 394
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience Paper • 2609.03241 • Published Sep 3 • 51