# ChatHTN: Interleaving Approximate (LLM) and Symbolic HTN Planning

arXiv: https://arxiv.org/abs/2505.11814 · HTML: https://mlsanity.com/paper/2505.11814/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 22 references that are in the map.
- First posted on arXiv 17 May 2025.

## Builds on (most cited first, 4 of 4)

- [Task and Motion Planning with Large Language Models for Object Rearrangement](https://mlsanity.com/paper/2303.06247/) (2023)
- [LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench](https://mlsanity.com/paper/2409.13373/) (2024)
- [Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1](https://mlsanity.com/paper/2410.02162/) (2024)
- [A Roadmap to Guide the Integration of LLMs in Hierarchical Planning](https://mlsanity.com/paper/2501.08068/) (2025)

## Built on by (most cited first, 7 of 7)

- [ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning](https://mlsanity.com/paper/2511.02424/) (2025)
- [ELHPlan: Efficient Long-Horizon Task Planning for Multi-Agent Collaboration](https://mlsanity.com/paper/2509.24230/) (2025)
- [Online Learning of HTN Methods for integrated LLM-HTN Planning](https://mlsanity.com/paper/2511.12901/) (2025)
- [Agents in the Large: Perception-Centered Architecture for Persistent Agents](https://mlsanity.com/paper/2608.30478/) (2026)
- [Towards a General Framework for HTN Modeling with LLMs](https://mlsanity.com/paper/2511.18165/) (2025)
- [Hierarchical Task Network Planning with LLM-Generated Heuristics](https://mlsanity.com/paper/2605.07707/) (2026)
- [HTN Planning as a Coordination Layer for Multi-Server MCP Tool Orchestration](https://mlsanity.com/paper/2609.33731/) (2026)

## Abstract (arXiv)

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.