ChatHTN: Interleaving Approximate (LLM) and Symbolic HTN Planning

2025/05/17 by Munoz-Avila, Hector, Aha, David W., Rizzo, Paola · 4 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2505.11814

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.

Cited by

• Towards a General Framework for HTN Modeling with LLMs
• Online Learning of HTN Methods for integrated LLM-HTN Planning
• ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning
• ELHPlan: Efficient Long-Horizon Task Planning for Multi-Agent Collaboration

Related

• Online Learning of HTN Methods for integrated LLM-HTN Planning
• Task Interaction in an HTN Planner
• HyperTensioN and Total-order Forward Decomposition optimizations
• Refining HTN Methods via Task Insertion with Preferences
• An Overview of Hierarchical Task Network Planning