一作ACL 2026Findings· Findings of ACL
Identifying Collective Intelligence Factor in LLM Agent Groups for Generalizable Multi-Agent System Design
Zhilun Zhou · Zihan Liu · Jiahe Liu · Yihan Wang · Qingyu Shao · Fengli Xu · Depeng Jin · Yong Li
摘要
Large language model (LLM)-based multi-agent systems (MASs) have shown impressive performance in solving a wide range of complex problems. However, previous studies mainly focus on designing customized MAS for specific tasks, while a critical research problem remains unclear: Do LLM agent groups...