2025/02/14 by Zhiyuan Li, Wenshuai Zhao, Li, Zhiyuan +3 · 1 citation
Computer Science · #AI-based Problem Solving and Planning #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Multi-Agent Systems and Negotiation #Multiagent Systems (cs.MA) #Robotic Path Planning Algorithms
paper · pdf · doi:10.48550/arxiv.2502.10148
openalex publication_date 2025/02/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Cooperative multi-agent reinforcement learning (MARL) struggles with sample efficiency, interpretability, and generalization. While Large Language Models (LLMs) offer powerful planning capabilities, their application has been hampered by a reliance on text-only inputs and a failure to handle the non-Markovian, partially observable nature of multi-agent tasks. We introduce COMPASS, a multi-agent framework that overcomes these limitations by integrating Vision-Language Models (VLMs) for decentralized, closed-loop decision-making. COMPASS dynamically generates and refines interpretable, code-based strategies stored in a skill library that is bootstrapped from expert demonstrations. To ensure robust coordination, it propagates entity information through a structured multi-hop communication protocol, allowing teams to build a coherent understanding from partial observations. Evaluated on the challenging SMACv2 benchmark, COMPASS significantly outperforms state-of-the-art MARL baselines. Notably, in the symmetric Protoss 5v5 task, COMPASS achieved a 57% win rate, a 30 percentage point advantage over QMIX (27%). Project page can be found at https://stellar-entremet-1720bb.netlify.app/.