Language-driven Coordination And Learning In Multi-agent Simulation Environments
2025 · Zhengyang Li, Sawyer Campos, Nana Wang
Abstract
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 polic
Authors
(none)
Tags
Stats
Related papers
- YOLO-MARL: You Only LLM Once For Multi-agent Reinforcement Learning (2024)0.00
- MARSHAL: Incentivizing Multi-agent Reasoning Via Self-play With Strategic Llms (2025)0.00
- Closed-loop Vision-language Planning For Multi-agent Coordination (2026)0.00
- Re-conceptualising The Language Game Paradigm In The Framework Of Multi-agent Reinforcement Learning (2020)0.00
- Towards Collaborative Intelligence: Propagating Intentions And Reasoning For Multi-agent Coordination With Large Language Models (2024)0.00
- End-to-end Optimization Of Llm-driven Multi-agent Search Systems Via Heterogeneous-group-based Reinforcement Learning (2025)0.00
- MAGE: Meta-reinforcement Learning For Language Agents Toward Strategic Exploration And Exploitation (2026)0.00
- Communicating Plans, Not Percepts: Scalable Multi-agent Coordination With Embodied World Models (2025)0.00