Generalized Planning in PDDL Domains with Pretrained Large Language Models
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (18) · 20256-20264
DOI: 10.1609/aaai.v38i18.30006 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Tom Silver und 5 weiteren Autor:innen. Die Arbeit wurde bisher 73-mal zitiert (Crossref).
Abstract (Originalsprache)
Recent work has considered whether large language models (LLMs) can function as planners: given a task, generate a plan. We investigate whether LLMs can serve as generalized planners: given a domain and training tasks, generate a program that efficiently produces plans for other tasks in the domain. In particular, we consider PDDL domains and use GPT-4 to synthesize Python programs. We also consider (1) Chain-of-Thought (CoT) summarization, where the LLM is prompted to summarize the domain and propose a strategy in words before synthesizing the program; and (2) automated debugging, where the program is validated with respect to the training tasks, and in case of errors, the LLM is re-prompted with four types of feedback. We evaluate this approach in seven PDDL domains and compare it to four ablations and four baselines. Overall, we find that GPT-4 is a surprisingly powerful generalized planner. We also conclude that automated debugging is very important, that CoT summarization has non-uniform impact, that GPT-4 is far superior to GPT-3.5, and that just two training tasks are often sufficient for strong generalization.
Zitieren
APA
Silver, T., Dan, S., Srinivas, K., Tenenbaum, J. B., Kaelbling, L., & Katz, M. (2024). Generalized Planning in PDDL Domains with Pretrained Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 38(18), 20256-20264. https://doi.org/10.1609/aaai.v38i18.30006
Vancouver
Silver T, Dan S, Srinivas K, Tenenbaum JB, Kaelbling L, Katz M. Generalized Planning in PDDL Domains with Pretrained Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(18):20256-20264. doi:10.1609/aaai.v38i18.30006
BibTeX
@article{Silver2024,
author = {Silver, Tom and Dan, Soham and Srinivas, Kavitha and Tenenbaum, Joshua B. and Kaelbling, Leslie and Katz, Michael},
title = {Generalized Planning in PDDL Domains with Pretrained Large Language Models},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {18},
pages = {20256--20264},
doi = {10.1609/aaai.v38i18.30006}
}
EUVIMED