Towards a General Framework for HTN Modeling with LLMs
This work addresses a specific bottleneck in automated planning for AI researchers, but it is incremental as it builds on existing methods with limited performance gains.
The authors tackled the gap in applying Large Language Models (LLMs) to Hierarchical Planning (HP) by proposing L2HP, an extension for generating HP models, and found that while parsing success is comparable to non-hierarchical planning (around 36%), syntactic validity is much lower in HP (1% vs. 20%).
The use of Large Language Models (LLMs) for generating Automated Planning (AP) models has been widely explored; however, their application to Hierarchical Planning (HP) is still far from reaching the level of sophistication observed in non-hierarchical architectures. In this work, we try to address this gap. We present two main contributions. First, we propose L2HP, an extension of L2P (a library to LLM-driven PDDL models generation) that support HP model generation and follows a design philosophy of generality and extensibility. Second, we apply our framework to perform experiments where we compare the modeling capabilities of LLMs for AP and HP. On the PlanBench dataset, results show that parsing success is limited but comparable in both settings (around 36\%), while syntactic validity is substantially lower in the hierarchical case (1\% vs. 20\% of instances). These findings underscore the unique challenges HP presents for LLMs, highlighting the need for further research to improve the quality of generated HP models.