Metraipolis › archive › dc_f68ce21169ee

From Natural Language Intent to Executable Control: Hierarchical Feedback-Guided LLM Planning for Multi-component Cyber-Physical Systems — arXiv:2610.22441

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22441
License (as archived)
CC0-1.0
Archived
2026-10-19T08:42:05.026Z
SHA-256 of the archived text
f51934c2bd9fbc5a436850c5039758688dea95aa942d0738c936d8b21fddbff2
Stable URL of this page
https://metraipolis.com/documento/dc_f68ce21169ee

How to cite

From Natural Language Intent to Executable Control: Hierarchical Feedback-Guided LLM Planning for Multi-component Cyber-Physical Systems — arXiv:2610.22441 — arXiv (en), https://arxiv.org/abs/2610.22441 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f68ce21169ee (Metraipolis archive dc_f68ce21169ee, sha256 f51934c2bd9fbc5a436850c5039758688dea95aa942d0738c936d8b21fddbff2)
BibTeX
@misc{dcf68ce21169ee,
  title = {From Natural Language Intent to Executable Control: Hierarchical Feedback-Guided LLM Planning for Multi-component Cyber-Physical Systems — arXiv:2610.22441},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22441},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f68ce21169ee; sha256 f51934c2bd9fbc5a436850c5039758688dea95aa942d0738c936d8b21fddbff2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22441. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) provide a convenient interface for translating natural language commands into task plans for cyber-physical systems (CPSs). However, two gaps hinder their use for real execution: generated plans may misinterpret or omit the user's intent, and even a logically plausible plan may be infeasible under component dynamics, interactions, or safety constraints. Existing LLM-based planning approaches often lack informative feedback on why a generated plan fails, providing little guidance for revising the plan accordingly. To address these challenges, we present a hierarchical feedback framework that uses different types of feedback information to guide LLMs in generating executable plans for CPSs. We prompt LLMs to generate both a structured task plan and corresponding signal temporal logic (STL) constraints, and design a sound algorithm that identifies definite contradictions between them and provides feedback for revising inconsistencies. At the execution level, when control synthesis fails, we extract different types of diagnostic information, such as violated constraints and conflicting component assignments, and feed them back to guide task replanning. Experiments on seven heterogeneous multi-component CPS scenarios have shown that our framework can generate executable plans and feasible control executions that satisfy the original natural language missions with a success rate of 87.9% with GPT-5.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.22441 — 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 2026-10-19T08:39:10.002Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).