Sep 2026
LLM-guided contrastive role representation for diverse multi-agent coordination
Experiments on the StarCraft Multi-Agent Challenge benchmark demonstrate that CLRE achieves superior win rates and sample efficiency compared with state-of-the-art MARL methods, showing that the proposed approach enables diverse and efficient cooperation among agents in complex environments.
Tingting Wei, Yan Zheng, Zhang-Ling Wang et al.
· Autonomous Agents and Multi-... · 0 citations