用大模型辅助生成任务分解，让符号规划更灵活可靠
ChatHTN: Interleaving Approximate (LLM) and Symbolic HTN Planning
- 将大模型查询与符号化任务网络规划交替使用
- 生成的计划能正确完成输入任务，保证结果正确性
- 适合需要灵活规划又要求结果可靠的场景
我们提出ChatHTN，一种结合符号化层级任务网络（HTN）规划与ChatGPT查询的规划系统，通过交替生成由符号规划和ChatGPT提供的任务分解，形成混合规划层次。尽管ChatGPT生成的结果具有近似性，但ChatHTN在理论上是保真的；其生成的任何计划均能正确达成初始任务目标。我们通过开源实现验证了该系统的有效性。
原文摘要 · Abstract (English)
We introduce ChatHTN, a Hierarchical Task Network (HTN) planner that combines symbolic HTN planning techniques with queries to ChatGPT to approximate solutions in the form of task decompositions. The resulting hierarchies interleave task decompositions generated by symbolic HTN planning with those generated by ChatGPT. Despite the approximate nature of the results generates by ChatGPT, ChatHTN is provably sound; any plan it generates correctly achieves the input tasks. We demonstrate this property with an open-source implementation of our system.
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。