Language-Driven Coordination and Learning in Multi-Agent Simulation Environments
It addresses the challenge of designing intelligent, cooperative agents for interactive simulations, offering a path for leveraging LLMs in multi-agent systems, though it appears incremental as it builds on existing MARL methods with LLM integration.
This paper tackles the problem of enhancing coordination and generalization in multi-agent reinforcement learning by introducing LLM-MARL, a framework that integrates large language models, resulting in consistent improvements in win rate, coordination score, and zero-shot generalization over baselines like MAPPO and QMIX in simulated game environments.
This paper introduces LLM-MARL, a unified framework that incorporates large language models (LLMs) into multi-agent reinforcement learning (MARL) to enhance coordination, communication, and generalization in simulated game environments. The framework features three modular components of Coordinator, Communicator, and Memory, which dynamically generate subgoals, facilitate symbolic inter-agent messaging, and support episodic recall. Training combines PPO with a language-conditioned loss and LLM query gating. LLM-MARL is evaluated in Google Research Football, MAgent Battle, and StarCraft II. Results show consistent improvements over MAPPO and QMIX in win rate, coordination score, and zero-shot generalization. Ablation studies demonstrate that subgoal generation and language-based messaging each contribute significantly to performance gains. Qualitative analysis reveals emergent behaviors such as role specialization and communication-driven tactics. By bridging language modeling and policy learning, this work contributes to the design of intelligent, cooperative agents in interactive simulations. It offers a path forward for leveraging LLMs in multi-agent systems used for training, games, and human-AI collaboration.