Large Language Models as Planning Domain Generators
This work addresses the bottleneck of manual domain modeling in AI planning, making planning more accessible, though it is incremental as it applies existing LLMs to a new task.
The paper tackles the problem of automating planning domain model generation by using large language models (LLMs) to create these models from textual descriptions, finding that high-parameter LLMs show moderate proficiency in generating correct domains across 9 planning domains.
Developing domain models is one of the few remaining places that require manual human labor in AI planning. Thus, in order to make planning more accessible, it is desirable to automate the process of domain model generation. To this end, we investigate if large language models (LLMs) can be used to generate planning domain models from simple textual descriptions. Specifically, we introduce a framework for automated evaluation of LLM-generated domains by comparing the sets of plans for domain instances. Finally, we perform an empirical analysis of 7 large language models, including coding and chat models across 9 different planning domains, and under three classes of natural language domain descriptions. Our results indicate that LLMs, particularly those with high parameter counts, exhibit a moderate level of proficiency in generating correct planning domains from natural language descriptions. Our code is available at https://github.com/IBM/NL2PDDL.