HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents Paper • 2610.23479 • Published 6 days ago • 312
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 23 days ago • 549
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 22 days ago • 644