ChatHTN: Interleaving Approximate (LLM) and Symbolic HTN Planning

Open Webpage

Hector Munoz-Avila

Published: 17 May 2025, Last Modified: 24 Mar 20262nd International Conference on Neuro-symbolic Systems (NeuS) 2025EveryonearXiv.org perpetual, non-exclusive license
Abstract: 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.