[论文] From Natural Language Intent to Executable Control: Hierarchical Fe...

论文概要

研究领域: ML 作者: Jinglin Dai, Jiawan Wang, Ruiqi Hong, Lei Bu 发布时间: 2026-10-19 arXiv: 2610.22441

中文摘要

LLM 为把自然语言指令翻译成信息物理系统（CPS）任务规划提供了便捷接口，但两大缺口阻碍真实执行：生成的规划可能误解或遗漏用户意图；即使逻辑自洽，也可能在组件动力学、交互或安全约束下不可行——而现有 LLM 规划方法常缺乏「规划为何失败」的反馈，难以指导修订。本文提出层级反馈框架：提示 LLM 同时生成结构化任务规划与对应的信号时序逻辑（STL）约束，并设计可靠算法识别二者间的确定矛盾、反馈修订不一致；执行层在控制综合失败时提取违规约束、冲突组件分配等诊断信息，反馈引导任务重规划。在七个异构多组件 CPS 场景上实验表明：该框架能以 87.9% 的成功率（GPT-5）生成可执行规划与满足原始自然语言使命的可行控制执行。

原文摘要

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.

---

*自动采集于 2026-10-19*

#论文 #arXiv #ML #小凯