Metraipolis › archive › dc_c4dd0302ada4
Compounding Physical RSI: Turning Execution Failure into Inherited Capability — arXiv:2611.06654
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06654
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:30:46.178Z
- SHA-256 of the archived text
0d4747d4957595e8d3288cdafb21c1296c666e0bd80ca8d63f0acba025c9fdfd- Stable URL of this page
https://metraipolis.com/documento/dc_c4dd0302ada4
How to cite
Compounding Physical RSI: Turning Execution Failure into Inherited Capability — arXiv:2611.06654 — arXiv (en), https://arxiv.org/abs/2611.06654 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c4dd0302ada4 (Metraipolis archive dc_c4dd0302ada4, sha256 0d4747d4957595e8d3288cdafb21c1296c666e0bd80ca8d63f0acba025c9fdfd)
BibTeX
@misc{dcc4dd0302ada4,
title = {Compounding Physical RSI: Turning Execution Failure into Inherited Capability — arXiv:2611.06654},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06654},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c4dd0302ada4; sha256 0d4747d4957595e8d3288cdafb21c1296c666e0bd80ca8d63f0acba025c9fdfd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06654. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generalist robot policies are trained on static offline datasets, yet physical manipulation unfolds sequentially across stages. Because a weakness in a downstream stage remains unobservable until the policy passes earlier ones, each resolved bottleneck exposes the next hidden failure mode. This staged structure calls for Recursive Self-Improvement (RSI), in which a policy iteratively executes, diagnoses failures, and updates itself. Moreover, because task completion behaves like a product of stage-level pass rates, recursive gains can multiply across generations. In physical environments, three bottlenecks obstruct compounding: terminal execution feedback rarely localizes the stage that caused a failure, failed trajectories do not supply the corrective action, and updating shared parameters can degrade previously mastered skills. We propose Compounding Physical RSI, a self-evolving policy framework that turns execution failures into heritable capability. First, automated capability-gap assessment traces failed rollouts to the task stage where progression breaks down and formulates a structured improvement objective. Second, conditioned on this objective, our remedy stage curates validated, stage-relevant experience and refines the policy via behavior-regularized offline reinforcement learning, without requiring costly online rollouts at each optimization step. Third, to safeguard existing skills, our retention stage constructs weight-space candidates between the inherited reference policy and the refined policy, evaluates them across the task suite, and promotes the best candidate as the reference state for the next generation. Evaluated across all 42 tasks of the RoboDojo-Sim benchmark, CSU-AI-07 ranks first on the leaderboard with a three-seed mean Overall Score of 26.15 and Success Rate of 20.70%, outperforming the next-best entry by 5.92 points and 5.82 percentage points. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2611.06654 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-05T18:20:03.991Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).