False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 10 days ago • 498
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 11 days ago • 490
Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering Paper • 2608.21450 • Published Aug 19 • 19
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs Paper • 2608.20492 • Published Aug 20 • 67