Understanding the planning of LLM agents: A survey

TL;DR

This survey reviews recent developments in using Large Language Models as planning modules for autonomous agents, categorizing approaches and discussing challenges in the field.

Contribution

It provides the first systematic taxonomy and analysis of LLM-based agent planning methods, highlighting key directions and future challenges.

Findings

Taxonomy of LLM-Agent planning approaches

Analysis of each planning category and its challenges

Discussion of future research directions

Abstract

As Large Language Models (LLMs) have shown significant intelligence, the progress to leverage LLMs as planning modules of autonomous agents has attracted more attention. This survey provides the first systematic view of LLM-based agents planning, covering recent works aiming to improve planning ability. We provide a taxonomy of existing works on LLM-Agent planning, which can be categorized into Task Decomposition, Plan Selection, External Module, Reflection and Memory. Comprehensive analyses are conducted for each direction, and further challenges for the field of research are discussed.