Abstract

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.

Keywords

Subject

Publication details

Journal
Not available
Open access
Green open access

Cite this article

APA 7

Xu, D., Hooi, B., & Qiao, D. (2026). When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate. https://omanscience.com/en/articles/when-order-matters-first-speaker-bias-and-mitigation-through-personality-in-sequential-multi-agent-debate

MLA 9

Xu, Duofeng, et al. "When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate." https://omanscience.com/en/articles/when-order-matters-first-speaker-bias-and-mitigation-through-personality-in-sequential-multi-agent-debate.

Chicago (author–date)

Xu, Duofeng, Bryan Hooi, and Dandan Qiao. 2026. "When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate." https://omanscience.com/en/articles/when-order-matters-first-speaker-bias-and-mitigation-through-personality-in-sequential-multi-agent-debate.

Harvard

Xu, D., Hooi, B. and Qiao, D. (2026) 'When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate', Available at: https://omanscience.com/en/articles/when-order-matters-first-speaker-bias-and-mitigation-through-personality-in-sequential-multi-agent-debate.

Vancouver

Xu D, Hooi B, Qiao D. When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate. https://omanscience.com/en/articles/when-order-matters-first-speaker-bias-and-mitigation-through-personality-in-sequential-multi-agent-debate

IEEE

D. Xu, B. Hooi, and D. Qiao, "When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate," https://omanscience.com/en/articles/when-order-matters-first-speaker-bias-and-mitigation-through-personality-in-sequential-multi-agent-debate.