A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application

TL;DR

This survey comprehensively reviews recent advances in LLM-based Multi-Agent Systems, covering their definitions, applications, challenges, and future research directions in a rapidly evolving field.

Contribution

It provides an up-to-date, structured overview of LLM-MAS research, integrating recent works and highlighting future challenges and opportunities.

Findings

LLM-MAS are used for complex task solving, scenario simulation, and agent evaluation.

The survey identifies key challenges in scalability, coordination, and evaluation.

Future research directions include improving system robustness and real-world applicability.

Abstract

LLM-based Multi-Agent Systems ( LLM-MAS ) have become a research hotspot since the rise of large language models (LLMs). However, with the continuous influx of new related works, the existing reviews struggle to capture them comprehensively. This paper presents a comprehensive survey of these studies. We first discuss the definition of LLM-MAS, a framework encompassing much of previous work. We provide an overview of the various applications of LLM-MAS in (i) solving complex tasks, (ii) simulating specific scenarios, and (iii) evaluating generative agents. Building on previous studies, we also highlight several challenges and propose future directions for research in this field.