AI RESEARCH
Demystifying Multi-Agent Debate: The Role of Confidence and Diversity
arXiv CS.AI
•
ArXi:2601.19921v2 Announce Type: replace-cross 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 improve outcomes.