WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution Paper • 2610.18067 • Published 10 days ago • 41
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 24 days ago • 207
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 23 days ago • 235
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 25 days ago • 220
srmistbiolab1991/visual-question-answering-study Visual Question Answering • 24.8k • Updated 27 days ago • 14
srmistbiolab1991/visual-question-answering-study Visual Question Answering • 24.8k • Updated 27 days ago • 14