LASP: Surveying the State-of-the-Art in Large Language Model-Assisted AI Planning

TL;DR

This survey reviews the current state of large language model-assisted AI planning, discussing challenges, applications, and future directions in leveraging LLMs for effective automated planning across various domains.

Contribution

It provides a comprehensive overview of how LLMs are transforming AI planning, highlighting key challenges and potential research directions.

Findings

Identifies challenges in plan reliability and execution.

Highlights applications in embodied environments and game strategies.

Discusses future research opportunities in LM-assisted planning.

Abstract

Effective planning is essential for the success of any task, from organizing a vacation to routing autonomous vehicles and developing corporate strategies. It involves setting goals, formulating plans, and allocating resources to achieve them. LLMs are particularly well-suited for automated planning due to their strong capabilities in commonsense reasoning. They can deduce a sequence of actions needed to achieve a goal from a given state and identify an effective course of action. However, it is frequently observed that plans generated through direct prompting often fail upon execution. Our survey aims to highlight the existing challenges in planning with language models, focusing on key areas such as embodied environments, optimal scheduling, competitive and cooperative games, task decomposition, reasoning, and planning. Through this study, we explore how LLMs transform AI planning and provide unique insights into the future of LM-assisted planning.