MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 17 days ago • 396
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 15 days ago • 664
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 16 days ago • 562
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published 16 days ago • 137
PAWBench: How Far Are We from Probabilistically Aligned World Modeling? Paper • 2608.27345 • Published Aug 27 • 62
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning Paper • 2608.26105 • Published Aug 26 • 151