LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions
This is an incremental survey paper aimed at researchers in AI and reinforcement learning, highlighting gaps and directions for integrating LLMs into multi-agent systems.
The paper surveys existing LLM-based single-agent and multi-agent reinforcement learning frameworks, focusing on cooperative tasks with communication and human-in-the-loop scenarios, to inspire future research in this area.
In recent years, Large Language Models (LLMs) have shown great abilities in various tasks, including question answering, arithmetic problem solving, and poem writing, among others. Although research on LLM-as-an-agent has shown that LLM can be applied to Reinforcement Learning (RL) and achieve decent results, the extension of LLM-based RL to Multi-Agent System (MAS) is not trivial, as many aspects, such as coordination and communication between agents, are not considered in the RL frameworks of a single agent. To inspire more research on LLM-based MARL, in this letter, we survey the existing LLM-based single-agent and multi-agent RL 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.