Metraipolis › archive › dc_386a72c604b4
Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents — arXiv:2609.37810
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37810
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:27:44.204Z
- SHA-256 of the archived text
3f5d9529236c251892c84aadb4484ccb80c42f53255a6697a1dd08a78e1ff3d6- Stable URL of this page
https://metraipolis.com/documento/dc_386a72c604b4
How to cite
Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents — arXiv:2609.37810 — arXiv (en), https://arxiv.org/abs/2609.37810 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_386a72c604b4 (Metraipolis archive dc_386a72c604b4, sha256 3f5d9529236c251892c84aadb4484ccb80c42f53255a6697a1dd08a78e1ff3d6)
BibTeX
@misc{dc386a72c604b4,
title = {Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents — arXiv:2609.37810},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37810},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_386a72c604b4; sha256 3f5d9529236c251892c84aadb4484ccb80c42f53255a6697a1dd08a78e1ff3d6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37810. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains challenging. More recently, general-purpose multimodal agents have shown great potential for zero-shot robotic task solving. However, they often incur high execution costs by reasoning and exploring the physical world from scratch. To reduce these costs, we introduce RoboSkill, a framework that connects skill acquisition and reuse through an Explore, Execute, Evolve loop. Within this loop, the agent explores to gather task-relevant information, executes tasks while adapting to feedback, and evolves its skill library based on execution records. It then reuses these skills to guide exploration and execution in the next cycle, closing the loop. To improve loop efficiency, we complement vision with tactile feedback to reduce uncertainty during physical interaction. We further augment textual guidance with reusable code to reduce reasoning overhead during skill reuse. On LIBERO-10, RoboSkill improves first-episode success rates by 12.5--25.0 percentage points and reduces average runtime by 7.6--72.4% across four agents. On real robots, it improves success rates by 8.3 percentage points and reduces average runtime for successful trials by at least 14.4%. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.37810 — 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 2026-10-07T15:54:54.031Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).