Understanding the Capabilities of Large Language Models for Automated Planning
This work addresses the problem of leveraging versatile LLMs for automated planning, which is incremental as it applies existing models to a new domain without introducing a novel method.
The paper investigates the use of Large Language Models (LLMs) for automated planning, exploring their capabilities in plan generation, effective pre-training data, fine-tuning vs. prompting approaches, and plan generalization, with results providing insights into effective methods for applying LLMs to complex planning problems.
Automated planning is concerned with developing efficient algorithms to generate plans or sequences of actions to achieve a specific goal in a given environment. Emerging Large Language Models (LLMs) can answer questions, write high-quality programming code, and predict protein folding, showcasing their versatility in solving various tasks beyond language-based problems. In this paper, we aim to explore how LLMs can also be used for automated planning. To do so, we seek to answer four key questions. Firstly, we want to understand the extent to which LLMs can be used for plan generation. Secondly, we aim to identify which pre-training data is most effective in facilitating plan generation. Thirdly, we investigate whether fine-tuning or prompting is a more effective approach for plan generation. Finally, we explore whether LLMs are capable of plan generalization. By answering these questions, the study seeks to shed light on the capabilities of LLMs in solving complex planning problems and provide insights into the most effective approaches for using LLMs in this context.