Metraipolis › archive › dc_68cd302cbb26

PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World — arXiv:2611.06768

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.06768
License (as archived): CC0-1.0
Archived: 2026-11-05T18:30:48.097Z
SHA-256 of the archived text: 9afed4e5915e747c74391162db487c3e8c8a90645c860d24494a66bc7b213a57
Stable URL of this page: https://metraipolis.com/documento/dc_68cd302cbb26

How to cite

PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World — arXiv:2611.06768 — arXiv (en), https://arxiv.org/abs/2611.06768 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_68cd302cbb26 (Metraipolis archive dc_68cd302cbb26, sha256 9afed4e5915e747c74391162db487c3e8c8a90645c860d24494a66bc7b213a57)

BibTeX

@misc{dc68cd302cbb26,
  title = {PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World — arXiv:2611.06768},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06768},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_68cd302cbb26; sha256 9afed4e5915e747c74391162db487c3e8c8a90645c860d24494a66bc7b213a57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06768. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Coding agents powered by models such as GPT-6-Astra connect spatial reasoning with executable robot behavior, raising the question of how such agents can produce lasting improvements in robot capabilities from physical interaction. In this work, we study embodied recursive self-improvement (RSI) through real-world exploration, code refinement, and deployment using PyRUA-REAL, a framework in which coding agents retain interaction experience as persistent memory and reusable executable skills that inform subsequent exploration and improvement. Our empirical study places physical manipulation at the center of the improvement process, examining how agents collaborate, what kinds of execution feedback support effective code refinement, and how task specifications and previously acquired skills influence robustness and task transfer. We further investigate the efficiency and capability of the resulting programs when deployed without involving an online agent for decision-making. Across eight real-world tasks, PyRUA-REAL achieves an average success rate of 91.1%. In complementary evaluation on 42 tasks from the RoboDojo benchmark, it achieves an average success rate of 84.4%. This study provides empirical guidance for turning physical exploration into reusable robot skills that support continued improvement and robust, efficient deployment.

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/2611.06768 — 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 2026-11-05T18:20:03.993Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).