Multi-LLM-Agents Debate - Performance, Efficiency, and Scaling Challenges

Hangfan Zhang, Zhiyao Cui, Qiaosheng Zhang, Shuyue Hu

Blogpost Url: https://d2jud02ci9yv69.cloudfront.net/2025-04-28-mad-159/blog/mad/

Abstract: Multi-Agent Debate (MAD) explores leveraging collaboration among multiple large language model (LLM) agents to improve test-time performance without additional training. This blog evaluates five MAD frameworks across nine benchmarks, revealing that current MAD methods fail to consistently outperform simpler single-agent strategies, even with increased computational resources. Analysis of factors such as agent configurations and debate rounds suggests that existing MAD designs fall short in fully utilizing additional inference-time computation.

Conflict Of Interest: N/A

Submission Number: 83