Multi-Agent Debate Does Not Outperform Single-Pass AI Feedback on Research Papers, Study Finds

Jul 17, 2026

A pre-registered experiment involving 44 meta-analyses in economics found that authors preferred feedback from a single-pass AI report over two multi-agent debate tools, even though the debate tools used up to 30 times more tokens. The single-pass approach was favored by 0.66 and 0.57 rank points over the two debate tools, respectively. The study also cautions against replacing human authors with AI judges, as AI judges' preferences differed from those of the authors.

Why it matters: This challenges the assumption that multi-agent debate improves AI feedback, raising questions about the effectiveness of such methods in peer review and research evaluation.

Full story at: arXiv Multiagent Systems ↗