MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 9 days ago • 412
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 8 days ago • 578
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 7 days ago • 672
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published 8 days ago • 140
ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation Paper • 2609.03756 • Published Sep 3 • 25