Metraipolis › archive › dc_edb90105643f
CoDA: Co-Evolution of Data Engines and Action Policies — arXiv:2610.22362
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22362
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:51:10.619Z
- SHA-256 of the archived text
726fb39d922dc67ba552bd97481fb11c814acf0b42367265b361c8c1ba4c92d4- Stable URL of this page
https://metraipolis.com/documento/dc_edb90105643f
How to cite
CoDA: Co-Evolution of Data Engines and Action Policies — arXiv:2610.22362 — arXiv (en), https://arxiv.org/abs/2610.22362 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edb90105643f (Metraipolis archive dc_edb90105643f, sha256 726fb39d922dc67ba552bd97481fb11c814acf0b42367265b361c8c1ba4c92d4)
BibTeX
@misc{dcedb90105643f,
title = {CoDA: Co-Evolution of Data Engines and Action Policies — arXiv:2610.22362},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22362},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edb90105643f; sha256 726fb39d922dc67ba552bd97481fb11c814acf0b42367265b361c8c1ba4c92d4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22362. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generative simulation can automate robot environment construction, but physically valid environments are not necessarily useful for training. The challenge is to identify environments that address a policy's failures and supervision that helps it overcome them. We introduce CoDA, a framework in which a simulation data engine and an action policy co-evolve through a shared heterogeneous memory of environment construction, policy failures, and learning progress. The memory compiles validated diagnoses from a vision-language critic into generation programs that recreate difficulties and training programs that help the policy overcome them. We further propose Text2potential to convert these diagnoses into staged potentials for action-chunk value learning, providing dense supervision for policy updates while preserving the task's optimal policy under standard shaping assumptions. Measured learning progress guides further generation and program refinement. Across four manipulation task families, CoDA improves out-of-distribution success from 5.3% after supervised fine-tuning to 27.6%, exceeding the strongest closed-loop baseline by 9.5 percentage points with the same generation budget. On LIBERO-Pro, 15 rounds of generation and training raise success from 25% to 84% under position perturbations and from 1% to 76% under instruction perturbations. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.22362 — 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 2026-10-16T08:44:18.068Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).