arXiv cs.AI· Jinglin Dai, Jiawan Wang, Ruiqi Hong, Lei Bu·· 12 小时前AI 评分31
从自然语言意图到可执行控制：面向多组件信息物理系统的分层反馈引导 LLM 规划
From Natural Language Intent to Executable Control: Hierarchical Feedback-Guided LLM Planning for Multi-component Cyber-Physical Systems
AI 导读
研究提出一种分层反馈框架，引导 LLM 为多组件信息物理系统（CPS）生成可执行计划：让模型同时输出结构化任务计划与对应的信号时序逻辑（STL）约束，并用算法识别二者矛盾、反馈修正；执行层控制合成失败时，提取违反约束、组件分配冲突等诊断信息回传以重新规划。在 7 个异构多组件 CPS 场景中，该框架配合 GPT-5 生成可执行计划与可行控制，任务成功率达 87.9%。
正文 · 原文
Abstract: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.
| Comments: | 20 pages, 6 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.22441 [cs.AI] |
| (or arXiv:2610.22441v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22441 arXiv-issued DOI via DataCite |
Submission history
From: Jinglin Dai [view email]
[v1]
Thu, 15 Oct 2026 14:52:57 UTC (7,591 KB)
来源：arXiv cs.AI · arxiv.org