1
Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exploration
大模型化身“导航员”，精准识别关键状态告别无效探索，显著提升多智能体协同效率
arXiv:2410.02511v2 Announce Type: replace Abstract: With expansive state-action spaces, efficient multi-agent exploration remains a longstanding chall…