Demystifying Multi-Agent Debate: The Role of Confidence and Diversity 事件

Demystifying Multi-Agent Debate: The Role of Confidence and Diversity arXiv:2601.19921v2 Announce Type: replace Abstract: 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 updates, debate preserves expected correctness and therefore cannot reliably impro