Keywords: Large language models, PDDL, AI Planning
TL;DR: We investigate the extent to which pretrained language models can solve PDDL planning problems on their own, or be used to guide a planner.
Abstract: We study few-shot prompting of pretrained large language models (LLMs) towards solving PDDL planning problems. We are interested in two questions: (1) To what extent can LLMs solve PDDL planning problems on their own? (2) How and to what extent can LLMs be used to guide AI planners? Recent work by Valmeekam et al. (2022) presents negative evidence for (1) in the classic blocks world domain. We confirm this finding, but expand the inquiry to 18 domains and find more mixed results with a few clear successes. For (2), we propose a simple mechanism for using good-but-imperfect LLM outputs to aid a heuristic-search planner. We also find that the LLM performance is due not only to syntactic pattern matching, but also to its commonsense understanding of English terms that appear in the PDDL.