Large Language Models as Planning Domain Generators

TL;DR

This paper explores using large language models to automatically generate planning domain models from natural language descriptions, aiming to reduce manual effort in AI planning.

Contribution

It introduces a framework for evaluating LLM-generated planning domains and empirically analyzes multiple models across various domains and descriptions.

Findings

High-parameter LLMs show moderate proficiency in domain generation.

Evaluation framework compares plan sets for generated domains.

Models perform better with detailed natural language descriptions.

Abstract

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.