Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning
DOI:
https://doi.org/10.1609/aaai.v38i18.29984Keywords:
PRS: Planning with Language Models, HAI: Learning Human Values and Preferences, HAI: Planning and Decision Support for Human-Machine Teams, PRS: ApplicationsAbstract
This is the first work to look at the application of large language models (LLMs) for the purpose of model space edits in automated planning tasks. To set the stage for this union, we explore two different flavors of model space problems that have been studied in the AI planning literature and explore the effect of an LLM on those tasks. We empirically demonstrate how the performance of an LLM contrasts with combinatorial search (CS) – an approach that has been traditionally used to solve model space tasks in planning, both with the LLM in the role of a standalone model space reasoner as well as in the role of a statistical signal in concert with the CS approach as part of a two-stage process. Our experiments show promising results suggesting further forays of LLMs into the exciting world of model space reasoning for planning tasks in the future.Downloads
Published
2024-03-24
How to Cite
Caglar, T., Belhaj, S., Chakraborty, T., Katz, M., & Sreedharan, S. (2024). Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(18), 20061-20069. https://doi.org/10.1609/aaai.v38i18.29984
Issue
Section
AAAI Technical Track on Planning, Routing, and Scheduling