# Hierarchical Task Network Planning with LLM-Generated Heuristics

arXiv: https://arxiv.org/abs/2605.07707 · HTML: https://mlsanity.com/paper/2605.07707/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 8 of 8)

- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code](https://mlsanity.com/paper/2503.18809/) (2025)
- [ChatHTN: Interleaving Approximate (LLM) and Symbolic HTN Planning](https://mlsanity.com/paper/2505.11814/) (2025)
- [An Accurate HDDL Domain Learning Algorithm from Partial and Noisy Observations](https://mlsanity.com/paper/2206.06882/) (2022)
- [HyperTensioN and Total-order Forward Decomposition optimizations](https://mlsanity.com/paper/2207.00345/) (2022)
- [Automatically Learning HTN Methods from Landmarks](https://mlsanity.com/paper/2404.06325/) (2024)
- [Large Language Models as Planning Domain Generators](https://mlsanity.com/paper/2405.06650/) (2024)
- [Online Learning of HTN Methods for integrated LLM-HTN Planning](https://mlsanity.com/paper/2511.12901/) (2025)

## Abstract (arXiv)

HTN planning is a variation of classical planning where, instead of searching for a linear sequence of actions, an algorithm decomposes higher-level tasks using a method library until only executable actions remain. On one hand, this allows one to introduce domain knowledge that can speed up the search for a solution through the method library. On the other hand, it creates challenges that go beyond those of classical state-space search. While recent research produced a number of heuristics and novel algorithms that speed up HTN planning, these heuristics are not yet as informative as those available in classical planning algorithms. We investigate whether large language models (LLMs) can generate effective search heuristics for HTN planning, extending the methodology of Correa, Pereira, and Seipp (2025) from classical to hierarchical planning. Using the Pytrich planner on six standard total-order HTN benchmark domains, we evaluate heuristics generated by nine LLMs under domain-specific prompting and compare them against the TDG and LMCount domain-independent baselines and the PANDA planner. Our results show that LLM-generated heuristics nearly match the coverage of the best available HTN planner, while substantially reducing search effort on 83% of shared problems.