arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.22277cs.HC
收藏

多智能体共识作为人类与人工智能交互中的认知偏差触发器

Multi-Agent Consensus as a Cognitive Bias Trigger in Human-AI Interaction

Department of Design, UNIST(蔚山科学技术院设计系)

Soohwan Lee, Kyungho Lee

AI总结:

研究探讨多智能体系统中共识机制对人类判断的影响,发现多数共识加速意见变化并提升自信,而少数反对则促进更深入的思考,揭示了智能体共识结构在人类与AI交互中的偏差相关信号作用。

摘要:

随着多智能体AI系统日益普及,用户逐渐面对集体而非单一AI声音,这种转变引入了共识、分歧和渐进收敛等社会动态,可能触发认知偏差并扭曲人类判断。本文通过一项受控实验(N=127)比较了三种多智能体配置:多数、少数和扩散。定量结果显示多数共识加速意见变化并提升自信,与社会证明和从众启发式一致。少数反对减缓这一过程并促进更深入的思考。定性分析识别出三种解释轨迹:强化、对齐和振荡,受用户如何解释智能体独立性和群体动态随时间变化的影响。这些发现表明,智能体共识结构,无论内容如何,都作为LLM交互中的偏差相关信号发挥作用。本文希望为Bias4Trust议程做出贡献,通过将多智能体社会影响作为具体且可设计的偏差来源,推动人类与AI交互的研究。

英文摘要:

As multi-agent AI systems become more common, users increasingly encounter not a single AI voice but a collective one. This shift introduces social dynamics, such as consensus, dissent, and gradual convergence, that can trigger cognitive biases and distort human judgment. We present findings from a controlled experiment (N = 127) comparing three multi-agent configurations: Majority, Minority, and Diffusion. Quantitative results show that majority consensus accelerates opinion change and inflates confidence, consistent with social proof and bandwagon heuristics. Minority dissent slows this process and promotes more deliberative engagement. Qualitative analysis identifies three interpretive trajectories: reinforcing, aligning, and oscillating, shaped by how users interpret agent independence and group dynamics over time. These findings suggest that agent agreement structure, independent of content, functions as a bias-relevant signal in LLM interactions. We hope this work contributes to the Bias4Trust agenda by grounding multi-agent social influence as a concrete and designable source of bias in human-AI interaction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑