顺序重要：多智能体顺序辩论中的首位发言者偏见及其通过人格特质的缓解

中文摘要 AI 辅助

多智能体辩论（MAD）常被用于提升大型语言模型（LLM）的推理能力，但顺序辩论很少是智能体意见的中性聚合器。我们表明，顺序式MAD存在显著的首位发言者偏见：当智能体首先发言时，其会不成比例地影响最终答案。因此，将更强的模型置于较弱模型之后，可能会大幅抵消其推理优势。随后，我们聚焦于不利的“强智能体最后发言”设置，并探究人格提示能否缓解这种不平衡。借鉴大五人格模型，我们研究了宜人性和外向性作为行为干预措施，分别应用于强方或弱方。我们发现，它们的效果具有特质特异性。影响力始终向较低宜人性方向转移，而将低宜人性分配给较强的智能体有助于恢复其失去的影响力并提高最终准确率。相比之下，外向性在影响力和准确率方面产生的系统性变化较少，其最明显的效果体现在智能体的冗长程度上。这些发现表明，有效的MAD设计不仅取决于模型能力，还取决于发言顺序和诱导的交互行为如何塑造辩论过程。

英文摘要

Multi-agent debate (MAD) is often used to improve large language model (LLM) reasoning, but sequential debate is rarely a neutral aggregator of agents' opinions. We show that sequential MAD suffers from a pronounced first-speaker bias: agents disproportionately shape the final answer when they speak first. As a result, placing a stronger model after weaker ones can substantially offset its reasoning advantage. We then focus on the disadvantaged strong-agent-last setting and ask whether personality prompting can mitigate this imbalance. Drawing on the Big Five model, we study agreeableness and extraversion as behavioral interventions applied to either the strong or weak side. We find that their effects are trait-specific. Influence consistently shifts in the direction of lower agreeableness, and assigning low agreeableness to the stronger agent helps restore its lost influence and improves final accuracy. Extraversion, by contrast, produces less systematic changes in influence and accuracy, with its clearest effect appearing in agents' verbosity. These findings show that effective MAD design depends not only on model capability, but also on how speaking order and induced interaction behavior shape the debate process.

发表机构

• School of Computing（计算学院）
• National University of Singapore（新加坡国立大学）

机构由 AI 辅助整理，请以论文原文为准。