On the Roles of LLMs in Planning: Embedding LLMs into Planning Graphs

TL;DR

This paper explores embedding large language models into graph-based planning frameworks, demonstrating their effectiveness in various domains and offering a novel approach to enhance planning capabilities.

Contribution

It introduces a new framework embedding LLMs into planning graphs at two levels, advancing the integration of LLMs with traditional planning methods.

Findings

LLMs improve planning efficiency in multiple domains.

Embedding LLMs enhances the quality of generated plans.

The proposed framework outperforms baseline methods.

Abstract

Plan synthesis aims to generate a course of actions or policies to transit given initial states to goal states, provided domain models that could be designed by experts or learnt from training data or interactions with the world. Intrigued by the claims of emergent planning capabilities in large language models (LLMs), works have been proposed to investigate the planning effectiveness of LLMs, without considering any utilization of off-the-shelf planning techniques in LLMs. In this paper, we aim to further study the insight of the planning capability of LLMs by investigating the roles of LLMs in off-the-shelf planning frameworks. To do this, we investigate the effectiveness of embedding LLMs into one of the well-known planning frameworks, graph-based planning, proposing a novel LLMs-based planning framework with LLMs embedded in two levels of planning graphs, i.e., mutual constraints generation level and constraints solving level. We empirically exhibit the effectiveness of our proposed framework in various planning domains.