对抗性影响在多智能体系统中如何扩展？

中文摘要 AI 辅助

多智能体协商可以提升性能，但当某些智能体不诚信行事时会发生什么？在实践中，智能体可能具有欺骗性，并致力于破坏群体，无论是通过其自身目标还是外部指令。我们研究了群体规模增大和欺骗者变得更加普遍时，对欺骗的敏感性如何变化。起作用的不是群体中智能体的数量，而是欺骗者的比例。我们观察到，变节率，即最初正确的智能体转向错误最终答案的频率，随这一比例线性上升。而在类似的人类从众研究中，只有当误导性的同谋者形成多数时，人类才会可靠地被左右，而LLM智能体即使欺骗者仍占少数时也会经常变节。敏感性还取决于哪些模型在交互，尤其是在诚实智能体一方。出乎意料的是，允许欺骗者私下协调可能使他们效果降低。总的来说，我们的结果表明，增加更多智能体因此并不是充分的防御，因为对手可以简单地随群体扩展。

英文摘要

Multi-agent deliberation can improve performance, but what happens when some agents do not act in good faith? In practice, an agent may be deceptive and work to subvert the group, whether through its own objectives or external instruction. We study how susceptibility to deception scales as groups increase in size and deceivers become more prevalent. It is not the number of agents in the group that matters, but the proportion of deceivers. We observe that the defection rate, how often initially correct agents switch to an incorrect final answer, rises linearly with this proportion. Whereas humans in comparable conformity studies are reliably swayed only when misleading confederates form a majority, LLM agents defect regularly even when deceivers remain a minority. Susceptibility also depends on which models are interacting, especially on the honest agent side. Unexpectedly, allowing deceivers to coordinate privately can make them less effective. Altogether, our results show that adding more agents is therefore not a sufficient defense, because the adversary can simply scale with the group.

发表机构

• Princeton University（普林斯顿大学）

机构由 AI 辅助整理，请以论文原文为准。