MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 8 days ago • 412
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 6 days ago • 480
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published 7 days ago • 139
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 7 days ago • 574
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement Paper • 2609.38721 • Published 6 days ago • 290
Running Featured 853 Agent Memory Leaderboard 🧠853 Unified memory evaluation · Results expected August 12.
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World Paper • 2608.13546 • Published Aug 13 • 143