Preprint
Oct 2026
RoboDoctor: Training-Free Recursive Self-Improvement for Robot Policies
Generalist robot policies and language-model agents provide complementary capabilities, but completing a task also requires adapting their use to the consequences of physical interaction. We study execution as a locus of adaptation: feedback guides the current action and supplies evidence for revising subsequent decisi...
He-Yang Yu, Hao-Min Li, Si-Hang Li et al.
· 0 citations