Metraipolis › archive › dc_381fe9eb6644

In-Context Learning for Robots: Methods and Applications — arXiv:2609.36012

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36012
License (as archived)
CC0-1.0
Archived
2026-10-07T17:32:27.770Z
SHA-256 of the archived text
c5d4ea164ec586e8003b4da1d8ffbdde39c463174304d37022223d815c2d5b3b
Stable URL of this page
https://metraipolis.com/documento/dc_381fe9eb6644

How to cite

In-Context Learning for Robots: Methods and Applications — arXiv:2609.36012 — arXiv (en), https://arxiv.org/abs/2609.36012 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_381fe9eb6644 (Metraipolis archive dc_381fe9eb6644, sha256 c5d4ea164ec586e8003b4da1d8ffbdde39c463174304d37022223d815c2d5b3b)
BibTeX
@misc{dc381fe9eb6644,
  title = {In-Context Learning for Robots: Methods and Applications — arXiv:2609.36012},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36012},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_381fe9eb6644; sha256 c5d4ea164ec586e8003b4da1d8ffbdde39c463174304d37022223d815c2d5b3b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36012. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL) for robots supports this process by using demonstrations and interaction to direct existing competence with neural parameters held fixed during deployment. We organize this literature review around the interfaces connecting contextual evidence to execution, distinguishing four families: context-conditioned policies, geometric demonstration transfer, world-model-based control, and skill- and agent-based execution. Comparing these interfaces clarifies their transfer assumptions and the roles of training, correspondence, and memory in making context useful. Across manipulation and navigation, we examine how these mechanisms preserve taught requirements as objects, environments, and execution conditions change. This analysis links method design to evaluation practices that distinguish responsiveness to teaching, physical transfer, and benefits from retained experience. The resulting agenda connects compositional task acquisition and faithful transfer with physical recursive self-improvement, in which experience improves the ability to learn subsequent tasks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.36012 — 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 2026-10-07T16:59:48.464Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).