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.

翻译：随着多智能体AI系统日益普及，用户面对的不再是单一的AI声音，而是集体性输出。这种转变引入了共识、异议与渐进趋同等社会动态，可能触发认知偏差并扭曲人类判断。我们通过一项受控实验（N=127）比较了三种多智能体配置：多数派、少数派与扩散模式。量化结果显示，多数派共识能加速观点转变并提升信心水平，这符合社会认同与从众启发式效应。少数派异议则减缓这一过程，促进更审慎的互动参与。质性分析识别出三种认知诠释轨迹：强化、校准与振荡——这些轨迹受用户随时间推移对智能体独立性与群体动态解读方式的塑造。研究表明，在LLM交互中，独立于内容本身的智能体协议结构，能成为与偏差相关的信号。我们期望这项工作通过将多智能体社会影响确认为人机交互中可具体设计化的偏差来源，为Bias4Trust议程作出贡献。