对比三种辩论协议，发现动态排序能更快达成共识。
The impact of multi-agent debate protocols on debate quality: a controlled case study
- 提出动态重排+静默机制的新型辩论协议
- 该协议收敛速度优于传统方法，且更易达成共识
- 适合追求决策一致性的场景，如经济预测
在多智能体辩论系统中，性能提升常被报告，但因辩论协议（如智能体数量、轮次、聚合规则）固定而模型因素变化，难以区分协议与模型的影响。为分离两者，我们对比三种主要协议：同轮可见（WR；仅见当前轮贡献）、跨轮可见（CR；完整前轮上下文），以及新提出的秩自适应跨轮（RA-CR；通过外部裁判模型动态重排并每轮静默一个智能体），并与无交互基线（NI；独立响应，无同伴可见性）比较。在20个不同宏观经济事件、五次随机种子、匹配提示/解码的受控案例研究中，RA-CR收敛速度优于CR，WR具有更高同伴引用率，而NI在论证多样性上最优（不受主协议影响）。结果揭示互动（同伴引用率）与收敛（共识形成）间的权衡，证实协议设计至关重要。当以共识优先时，RA-CR表现最佳。
原文摘要 · Abstract (English)
In multi-agent debate (MAD) systems, performance gains are often reported; however, because the debate protocol (e.g., number of agents, rounds, and aggregation rule) is typically held fixed while model-related factors vary, it is difficult to disentangle protocol effects from model effects. To isolate these effects, we compare three main protocols, Within-Round (WR; agents see only current-round contributions), Cross-Round (CR; full prior-round context), and novel Rank-Adaptive Cross-Round (RA-CR; dynamically reorders agents and silences one per round via an external judge model), against a No-Interaction baseline (NI; independent responses without peer visibility). In a controlled macroeconomic case study (20 diverse events, five random seeds, matched prompts/decoding), RA-CR achieves faster convergence than CR, WR shows higher peer-referencing, and NI maximizes Argument Diversity (unaffected across the main protocols). These results reveal a trade-off between interaction (peer-referencing rate) and convergence (consensus formation), confirming protocol design matters. When consensus is prioritized, RA-CR outperforms the others.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。