{"arxiv_id":"2610.35604","title":"RoboDoctor: Training-Free Recursive Self-Improvement for Robot Policies","abstract":"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 decisions under fixed model weights. We introduce RoboDoctor, a training-free framework that connects diagnosis, grounded action, and persistent experience across three revision targets. The harness allocates control between policy and agent; intervention determines when to assist while preserving useful policy behavior; and operation refines physical methods through observed effects. Linked experience records retain the reason for a decision, the attempted method, its outcome, and conditions for reuse. On a curated archive of 54 RoboDojo-Sim task entries, RoboDoctor achieves a five-dimension mean score of 57.10, with a native success rate of 49.44%. Recorded interactions illustrate strategy changes, selective correction, and grasp revision. These findings characterize execution-time adaptation in the evaluated system; controlled trials remain necessary to isolate the contribution of cross-episode experience.","primary_cat":"cs.RO","cross_cats":["cs.CV"],"submitted_at":"2026-10-26T15:27:20+00:00","latest_version":1,"source":"arxiv","source_label":"arXiv","source_url":null,"has_pdf":true,"has_source":false,"verdict":"CONDITIONAL","confidence":"MODERATE","one_line_summary":"A training-free 'doctor' reviews, corrects, and reuses execution experience around a frozen robot policy, reporting 57.10 on 54 RoboDojo-Sim tasks, though the causal benefit of experience reuse is unmeasured.","novelty_score":5.0,"correctness_risk":"medium","formal_verification":"none","upvotes":0,"downvotes":0,"pith_score":0,"inbound_count":1,"_links":{"html":"https://pith.science/paper/2610.35604","verdict":"/api/v1/verdicts/2610.35604"}}