Multi-Agent LLMs Struggle with Exploration, MACE Framework Proposed

Jul 14, 2026

A new preprint finds that large language model (LLM) agents in multi-agent environments often fail to explore each other's capabilities, resulting in myopic and polarized interactions and suboptimal coordination. The authors formalize this as the Multi-Agent Exploration problem and introduce MACE, a framework that encourages structured peer selection to improve exploration and task performance. Theoretical and empirical results show that MACE leads to better exploration, especially as agent diversity increases.

Why it matters: This work reveals a key limitation in current LLM-based multi-agent systems and proposes a practical framework to enhance their coordination and reliability.

Full story at: arXiv Multiagent Systems ↗