利用环境交互实现基于大语言模型的自动PDDL转换与规划
Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models
AI总结：
提出利用环境反馈自动生成PDDL文件的方法，通过迭代细化和探索行走指标，在10个环境中达到66%的任务解决率，显著优于GPT-4的29%。
摘要：
大语言模型（LLMs）在各种自然语言任务中表现出色，但在需要结构化推理的规划问题上往往力不从心。为解决这一局限，将规划问题转换为规划域定义语言（PDDL）已被提出作为潜在解决方案，从而能够使用自动规划器。然而，生成准确的PDDL文件通常需要人工输入或修正，这既耗时又昂贵。本文提出了一种新颖方法，利用LLMs和环境反馈自动生成PDDL域和问题描述文件，无需人工干预。我们的方法引入了一个迭代细化过程，生成多个问题PDDL候选，并基于与环境交互获得的反馈逐步细化域PDDL。为引导细化过程，我们开发了探索行走（EW）指标，为LLMs提供丰富的反馈信号以更新PDDL文件。我们在10个PDDL环境中评估了该方法。我们实现了平均任务解决率66%，而GPT-4通过思维链提示的内在规划解决率为29%。我们的工作利用LLMs和环境反馈实现了规划环境的自动建模，消除了PDDL转换过程中对人工干预的需求，为在挑战性问题中构建更可靠的LLM智能体铺平了道路。我们的代码可在https://github.com/BorealisAI/llm-pddl-planning获取。
英文摘要：
Large Language Models (LLMs) have shown remarkable performance in various natural language tasks, but they often struggle with planning problems that require structured reasoning. To address this limitation, the conversion of planning problems into the Planning Domain Definition Language (PDDL) has been proposed as a potential solution, enabling the use of automated planners. However, generating accurate PDDL files typically demands human inputs or correction, which can be time-consuming and costly. In this paper, we propose a novel approach that leverages LLMs and environment feedback to automatically generate PDDL domain and problem description files without the need for human intervention. Our method introduces an iterative refinement process that generates multiple problem PDDL candidates and progressively refines the domain PDDL based on feedback obtained from interacting with the environment. To guide the refinement process, we develop an Exploration Walk (EW) metric, which provides rich feedback signals for LLMs to update the PDDL file. We evaluate our approach on $10$ PDDL environments. We achieve an average task solve rate of 66% compared to a 29% solve rate by GPT-4's intrinsic planning with chain-of-thought prompting. Our work enables the automated modeling of planning environments using LLMs and environment feedback, eliminating the need for human intervention in the PDDL translation process and paving the way for more reliable LLM agents in challenging problems. Our code is available at https://github.com/BorealisAI/llm-pddl-planning
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
