False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 150
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems Paper • 2609.33325 • Published Sep 27 • 58
PAWBench: How Far Are We from Probabilistically Aligned World Modeling? Paper • 2608.27345 • Published Aug 27 • 35