False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 22 days ago • 644
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 23 days ago • 549
VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models Paper • 2609.32607 • Published 26 days ago • 135
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 24 days ago • 368