ChatHTN: Interleaving Approximate (LLM) and Symbolic HTN Planning
This work addresses planning challenges in AI by integrating approximate LLM methods with symbolic techniques, though it appears incremental as it builds on existing HTN frameworks.
The paper tackles the problem of generating hierarchical task decompositions by combining symbolic HTN planning with ChatGPT queries, resulting in a system that is provably sound and correctly achieves input tasks, as demonstrated with an open-source implementation.
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.