Metraipolis › archive › dc_cfd10b217944
Co-Evolving Robot Orchestrators and Policies through Deployment — arXiv:2610.09228
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09228
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:48:55.642Z
- SHA-256 of the archived text
eea74b3b2a5469ea8a542e4fa9d412e3bbfb1b7e4249c5d9722dc0f9f7d24a91- Stable URL of this page
https://metraipolis.com/documento/dc_cfd10b217944
How to cite
Co-Evolving Robot Orchestrators and Policies through Deployment — arXiv:2610.09228 — arXiv (en), https://arxiv.org/abs/2610.09228 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cfd10b217944 (Metraipolis archive dc_cfd10b217944, sha256 eea74b3b2a5469ea8a542e4fa9d412e3bbfb1b7e4249c5d9722dc0f9f7d24a91)
BibTeX
@misc{dccfd10b217944,
title = {Co-Evolving Robot Orchestrators and Policies through Deployment — arXiv:2610.09228},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09228},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cfd10b217944; sha256 eea74b3b2a5469ea8a542e4fa9d412e3bbfb1b7e4249c5d9722dc0f9f7d24a91},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09228. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-language-action (VLA) policies trained on large datasets are capable within their training domains, yet they still fail to generalize to the variety of situations a robot meets in real-world deployment. Agentic robot systems complement the policy with a vision-language model (VLM) orchestrator that learns when to call the policy, how to instruct it, and when to use scripted skills instead. However, because the harness is built around a frozen policy that has limited language steerability, the orchestrator can avoid the policy's failures but never overcome them. The policy becomes the bottleneck of the whole system. Fine-tuning the policy can remove this bottleneck, but updating it alone decouples it from an orchestrator tuned to its old behavior. We propose Robo-COP, in which the orchestrator and policy co-evolve during deployment. Robo-COP curates skill demonstrations from its own executions, fine-tunes the policy when this data can address recurring failures, and adopts each new policy only after it improves the skills it was trained for. Across ten simulated RoboLab tasks, Robo-COP raises mean held-out success from 64.8% to 73.8% over the same harness with a frozen policy, while fine-tuning on a fixed schedule without verification reaches only 65.8%. On three real-world tasks, Robo-COP raises held-out success from 38.3% to 50.0%. Robo-COP turns deployment into a self-improving flywheel in which robots learn by doing, with each improvement in execution producing better data for the next round of learning. Videos and code are available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2610.09228 — 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 2026-10-08T12:18:30.507Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).