LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
Bo Liu∗†, Yuqian Jiang∗†, Xiaohan Zhang‡, Qiang Liu†, Shiqi Zhang‡, Joydeep Biswas†, Peter Stone†§ *Equal contribution.†Department of Computer Science, The University of Texas at Austin {bliu, lqiang, joydeep, of Computer Science, State University of New York at Binghamton §Sony AI
Abstract
Large language models (LLMs) have demonstrated remarkable zero-shot generalization abilities: state-of-the-art chatbots can provide plausible answers to many common questions that arise in daily life. However, so far, LLMs cannot reliably solve long-horizon robot planning problems. By contrast, classical planners, once a problem is given in a formatted way, can use efficient search algorithms to quickly identify correct, or even optimal, plans. In an effort to get the best of both worlds, this paper introduces LLM+P, the first framework that incorporates the strengths of classical planners into LLMs. LLM+P takes in a natural language description of a planning problem, then returns a correct (or optimal) plan for solving that problem in natural language. LLM+P does so by first converting the language description into a file written in the planning domain definition language (PDDL), then leveraging classical planners to quickly find a solution, and then translating the found solution back into natural language. Along with LLM+P, we define a diverse set of different benchmark problems taken from robot planning scenarios. Via a comprehensive set of experiments on these benchmark proble
中文速览
大型语言模型（LLM）虽然在日常对话中表现出色，但在需要多步推理的机器人规划任务上往往给出错误甚至不可行的方案。为了解决这个问题，研究者提出了 LLM+P 框架：先让 LLM 将用自然语言描述的规划任务翻译成标准化的规划领域定义语言（PDDL）文件，再调用经典符号规划器（classical planner）求解，最后由 LLM 把规划结果翻译回自然语言返回给用户。在涵盖多种机器人场景的基准测试中，LLM+P 能为绝大多数问题给出最优解，而单独使用 LLM 连可行解都难以保证；此外，该框架还被成功应用于让家用机器人执行用户以自然语言描述的复杂操作任务。这项工作的价值在于它提供了一种无需修改或微调 LLM 本身、却能大幅提升其规划可靠性的通用思路，也为未来将 LLM 与其他可靠求解工具结合奠定了方法论基础。
原文 arXiv:2304.11477;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2304.11477v3