作者位次 #3/6ACL 2026Findings· Findings of ACL
Demystifying Multi-Agent Debate: The Role of Confidence and Diversity
Xiaochen Zhu · Caiqi Zhang · Yizhou Chi · Tom Stafford · Nigel Collier · Andreas Vlachos
摘要
Multi-agent debate (MAD) is widely used to improve large language model (LLM) performance through test-time scaling, yet recent work shows that vanilla MAD often underperforms simple majority vote despite higher computational cost. Studies show that, under homogeneous agents and uniform belief up...