arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.18498cs.MAcs.GT
收藏

混合群体中公平性的演化与专门化AI代理

Evolution of fairness in hybrid populations with specialised AI agents

Teesside University(蒂斯赛德大学);University of Stirling(斯特灵大学);Faculty of Engineering Sciences, Kyushu University(九州大学工学研究院)

Zhao Song, Theodor Cimpeanu, Chen Shen, The Anh Han

AI总结:

研究提出一种混合群体模型,通过设计歧视型AI提议者,有效提升混合社会中的公平性水平。

摘要:

混合社会中的公平性取决于一个简单选择:AI应是慷慨的东道主还是严格的守门人?超越对称模型,我们展示出不对称的社会结构——如招聘、监管和谈判——中,守护公平性的AI优于馈赠公平性的AI。我们通过一个双部分混合群体模型来弥合这一差距,该模型用于最后通牒博弈,将人类和AI分为不同的提议者和接收者群体。我们首先引入仁慈型AI代理,它们既可以作为无条件公平的提议者,也可以作为严格接收者。我们的结果揭示出显著的不对称性:仁慈型AI接收者在群体层面推动公平性远比仁慈型AI提议者更有效。为了克服仁慈型AI提议者的局限性,我们设计了歧视型AI提议者,它能预测合作者的期望,并只向接受阈值高的个体提供公平份额。我们的结果表明,这种歧视型AI在两种仁慈型AI中均表现更优,尤其是在强选择场景中。它不仅在两个群体中维持公平性,还能显著降低达到公平稳态所需代理的临界质量。通过从无条件建模转向战略执行,我们的工作为在日益混合的社会中部署不对称AI提供了关键框架。

英文摘要:

Fairness in hybrid societies hinges on a simple choice: should AI be a generous host or a strict gatekeeper? Moving beyond symmetric models, we show that asymmetric social structures--like those in hiring, regulation, and negotiation--AI that guards fairness outperforms AI that gifts it. We bridge this gap with a bipartite hybrid population model of the Ultimatum Game, separating humans and AI into distinct proposer and receiver groups. We first introduce Samaritan AI agents, which act as either unconditional fair proposers or strict receivers. Our results reveal a striking asymmetry: Samaritan AI receivers drive population-wide fairness far more effectively than Samaritan AI proposers. To overcome the limitations of the Samaritan AI proposer, we design the Discriminatory AI proposer, which predicts co-players' expectations and only offers fair portions to those with high acceptance thresholds. Our results demonstrate that this Discriminatory AI outperforms both types of Samaritan AI, especially in strong selection scenarios. It not only sustains fairness across both populations but also significantly lowers the critical mass of agents required to reach an equitable steady state. By transitioning from unconditional modelling to strategic enforcement, our work provides a pivotal framework for deploying asymmetric AIs in the increasingly hybrid society.

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。

↑