A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
It provides an updated overview for researchers in AI and multi-agent systems, but is incremental as it synthesizes existing work without new empirical results.
This paper presents a comprehensive survey of LLM-based Multi-Agent Systems (LLM-MAS), addressing the gap in existing reviews by covering recent advances and applications in complex tasks, scenario simulation, and agent evaluation, while also identifying challenges and future research directions.
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.