Metraipolis › archive › dc_720eb25a4590

Adaptive Code Generation for Controlling Robots — arXiv:2610.09588

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09588
License (as archived)
CC0-1.0
Archived
2026-10-08T11:11:15.177Z
SHA-256 of the archived text
6c618197f896ede96315eee8e5a54ca2f0dc83b639378d40f303205fe14bd438
Stable URL of this page
https://metraipolis.com/documento/dc_720eb25a4590

How to cite

Adaptive Code Generation for Controlling Robots — arXiv:2610.09588 — arXiv (en), https://arxiv.org/abs/2610.09588 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_720eb25a4590 (Metraipolis archive dc_720eb25a4590, sha256 6c618197f896ede96315eee8e5a54ca2f0dc83b639378d40f303205fe14bd438)
BibTeX
@misc{dc720eb25a4590,
  title = {Adaptive Code Generation for Controlling Robots — arXiv:2610.09588},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09588},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_720eb25a4590; sha256 6c618197f896ede96315eee8e5a54ca2f0dc83b639378d40f303205fe14bd438},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09588. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deploying robots as Complex Adaptive Systems (CAS) in unknown and dynamic environments necessitates a transition from rigid command libraries toward intention-based autonomy, as natural language represents the only medium capable of articulating complex goals beyond the capacity of finite instruction sets. While Large Language Models (LLMs) offer a path toward natural language goal description, their integration introduces significant challenges: the formalization gap between imprecise intentions and executable actions, the taxonomy gap induced by unpredictable environments, and the challenge of maintaining temporal state and progress awareness. This work introduces an architectural framework that enables robotic control by leveraging generative AI. The system follows a dual-AI design: an LLM translates high-level intentions into executable program code restricted to a formal robotic library and constrained by verifiable syntax, while a Vision-Language Model (VLM) provides semantic grounding via a distillation process. To ensure robustness, the framework incorporates environment-driven replanning triggers based on geometric and semantic thresholds, complemented by continuous runtime monitoring and an adaptive planning loop. Benchmarked across frontier models, our framework architecture demonstrates that grounding generative AI in a reactive, constrained loop enables robust fulfillment of complex intentions in dynamic and unknown environments.

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/2610.09588 — 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 2026-10-08T10:14:06.106Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).