引导大型语言模型在分层规划中整合的路线图
A Roadmap to Guide the Integration of LLMs in Hierarchical Planning
AI总结：
本文提出了一条引导大型语言模型在分层规划中整合的路线图，通过分类整合方法和建立基准测试，探索LLMs在分层规划中的应用潜力。
摘要：
近年来，大型语言模型（LLMs）的进步正在推动其在多个推理相关领域中的整合，包括自动规划（AP）。然而，其在分层规划（HP），即自动规划的一个子领域，该领域利用分层知识来增强规划性能，仍鲜有探索。在本初步工作中，我们提出了一条路线图，以解决这一差距，并利用LLMs的潜力来推动HP的发展。为此，我们提出了整合方法的分类，探讨LLMs如何在HP生命周期内被利用。此外，我们提供了一个具有标准化数据集的基准，用于评估未来基于LLMs的HP方法的性能，并展示了当前最先进的HP规划器和LLMs规划器的初步结果。正如预期的那样，后者表现有限（3%的正确计划，且无正确的分层分解），但为未来的方法提供了有价值的基线。
英文摘要：
Recent advances in Large Language Models (LLMs) are fostering their integration into several reasoning-related fields, including Automated Planning (AP). However, their integration into Hierarchical Planning (HP), a subfield of AP that leverages hierarchical knowledge to enhance planning performance, remains largely unexplored. In this preliminary work, we propose a roadmap to address this gap and harness the potential of LLMs for HP. To this end, we present a taxonomy of integration methods, exploring how LLMs can be utilized within the HP life cycle. Additionally, we provide a benchmark with a standardized dataset for evaluating the performance of future LLM-based HP approaches, and present initial results for a state-of-the-art HP planner and LLM planner. As expected, the latter exhibits limited performance (3\% correct plans, and none with a correct hierarchical decomposition) but serves as a valuable baseline for future approaches.
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。
