# Online Learning of HTN Methods for integrated LLM-HTN Planning

arXiv: https://arxiv.org/abs/2511.12901 · HTML: https://mlsanity.com/paper/2511.12901/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 30 references that are in the map.
- First posted on arXiv 17 Nov 2025.

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

- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks](https://mlsanity.com/paper/2402.08115/) (2024)
- [VAL: Interactive Task Learning with GPT Dialog Parsing](https://mlsanity.com/paper/2310.01627/) (2023)
- [ChatHTN: Interleaving Approximate (LLM) and Symbolic HTN Planning](https://mlsanity.com/paper/2505.11814/) (2025)

## Built on by (most cited first, 1 of 1)

- [Hierarchical Task Network Planning with LLM-Generated Heuristics](https://mlsanity.com/paper/2605.07707/) (2026)

## Abstract (arXiv)

We present online learning of Hierarchical Task Network (HTN) methods in the context of integrated HTN planning and LLM-based chatbots. Methods indicate when and how to decompose tasks into subtasks. Our method learner is built on top of the ChatHTN planner. ChatHTN queries ChatGPT to generate a decomposition of a task into primitive tasks when no applicable method for the task is available. In this work, we extend ChatHTN. Namely, when ChatGPT generates a task decomposition, ChatHTN learns from it, akin to memoization. However, unlike memoization, it learns a generalized method that applies not only to the specific instance encountered, but to other instances of the same task. We conduct experiments on two domains and demonstrate that our online learning procedure reduces the number of calls to ChatGPT while solving at least as many problems, and in some cases, even more.