Metraipolis › archive › dc_a4dfc79770bb
In-Context Robot Learning with VLM Agents — arXiv:2609.19138
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19138
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T16:16:47.107Z
- SHA-256 of the archived text
40ef98aba4e4261cd2d6164bcef68706f3cacacb6efe29984ddc27ffe5d38a53- Stable URL of this page
https://metraipolis.com/documento/dc_a4dfc79770bb
How to cite
In-Context Robot Learning with VLM Agents — arXiv:2609.19138 — arXiv (en), https://arxiv.org/abs/2609.19138 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4dfc79770bb (Metraipolis archive dc_a4dfc79770bb, sha256 40ef98aba4e4261cd2d6164bcef68706f3cacacb6efe29984ddc27ffe5d38a53)
BibTeX
@misc{dca4dfc79770bb,
title = {In-Context Robot Learning with VLM Agents — arXiv:2609.19138},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19138},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4dfc79770bb; sha256 40ef98aba4e4261cd2d6164bcef68706f3cacacb6efe29984ddc27ffe5d38a53},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19138. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No finite collection of demonstrations can cover every task and situation a robot will encounter, making the ability to learn from context at deployment essential for generalization. Such in-context learning (ICL), however, remains largely beyond the reach of existing robotic policies. The broad agentic capabilities of commercial vision-language models (VLMs), such as GPT-6 Astra, raise a compelling question: can these models learn from demonstrations, examples, and interaction feedback, then translate that information into executable and verifiable robot behavior from a new initial state without gradient updates or persistent changes to task-specific parameters? We introduce GPT-Policy, a general-agent framework for in-context robot learning. GPT-Policy integrates a context compiler that preserves task-relevant visual transitions, a VLM that proposes robot-tool actions, and a constrained controller that verifies and executes each action and reports its outcome. We evaluate its reliability and limitations through task success and efficiency metrics, matched comparisons across models, and controlled context ablations. In real-robot trials, human video demonstrations improve task completion even without robot action labels, while aligned action references yield further gains on contact-sensitive tasks. These findings position GPT-Policy as a step toward robot adaptation through in-context learning, providing an empirical foundation for translating the general-purpose capabilities of VLMs into physical behavior and clarifying the challenges that must be overcome for reliable deployment. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.19138 — 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 2026-10-15T15:45:19.835Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).