The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 2 days ago • 205
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 1 day ago • 92
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 3 days ago • 384
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published 2 days ago • 65
Edge0/Edge0-35B-A3B-preview Text Generation • 35B • Updated about 2 hours ago • 80.1k • 3.56k
Show-Harness: Just a VLM Agent Can Play Robots Paper • 2609.10522 • Published 22 days ago • 161