Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models Paper • 2609.39820 • Published 12 days ago • 31
How to Loop MoE: Flatten the Experts, Untie the Attention Paper • 2609.35751 • Published 14 days ago • 13
WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents Paper • 2609.40325 • Published 12 days ago • 106
Recursive Harness Distillation across Agents for Robot Manipulation Paper • 2609.33378 • Published 15 days ago • 42