LLM-Based Multi-Agent Decision-Making: Challenges and Future Directions

Abstract

In recent years, Large Language Models (LLMs) have shown great abilities in various tasks, including question answering, arithmetic problem solving, and poetry writing, among others. Although research on LLM-as-an-agent has shown that LLM can be applied to Decision-Making (DM) and achieve decent results, the extension of LLM-based agents to Multi-Agent DM (MADM) is not trivial, as many aspects, such as coordination and communication between agents, are not considered in the DM frameworks of a single agent. To inspire more research on LLM-based MADM, in this letter, we survey the existing LLM-based single-agent and multi-agent decision-making frameworks and provide potential research directions for future research. In particular, we focus on the cooperative tasks of multiple agents with a common goal and communication among them. We also consider human-in/on-the-loop scenarios enabled by the language component in the framework.