为大模型融入分层规划提供路线图与评估基准
A Roadmap to Guide the Integration of LLMs in Hierarchical Planning
- 提出分层规划中大模型融合的分类体系
- 构建标准化数据集，验证现有方法仅3%计划正确
- 为后续研究提供可复现的基线与评估框架
大语言模型（LLMs）在推理相关领域的进展正推动其在自动规划（AP）中的应用。然而，其在分层规划（HP）——利用层级知识提升规划性能的子领域——中的整合仍处于空白状态。本文初步提出一条整合路线图，旨在填补这一空白并挖掘LLMs在HP中的潜力。我们构建了集成方法的分类体系，探索LLMs在HP生命周期中的应用方式；同时提供一个标准化数据集作为评估基准，用于衡量未来基于LLMs的HP方法表现。实验结果显示，当前最先进的HP规划器与LLM规划器均表现有限：后者仅生成3%的正确计划，且无一具备正确的层级分解结构。尽管如此，该结果仍为后续研究提供了关键基准。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。