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 2603.13876cs.MAcs.CY
收藏

角色榜样如何塑造集体道德?多智能体模拟中的范例驱动道德学习

How do Role Models Shape Collective Morality? Exemplar-Driven Moral Learning in Multi-Agent Simulation

Beijing Normal University(北京师范大学);University of California, Los Angeles(加州大学洛杉矶分校);Peking University(北京大学)

Junjie Liao, Huacong Tang, Zhou Ziheng, Yizhou Wang, Fangwei Zhong

AI总结:

本文通过多智能体模拟研究角色榜样对集体道德的影响,发现身份驱动的从众行为能迅速改变初始倾向,推动价值观趋同。

摘要:

我们需要榜样吗?榜样如何塑造集体道德?为探讨这些问题,我们构建了一个由大型语言模型驱动的多智能体模拟系统,其中具有从合作到竞争等不同内在驱动力的智能体通过四阶段认知循环(计划-行动-观察-反思)进行交互和适应。我们设计了四个实验游戏(对齐、崩溃、冲突和建设)并进行了动机消融研究,以识别模仿的关键驱动因素。结果表明,身份驱动的从众行为可以强烈地超越初始倾向。智能体会持续调整其价值观以与感知到的成功范例一致,导致快速的价值观趋同。

英文摘要:

Do We Need Role Models? How do Role Models Shape Collective Morality? To explore the questions, we build a multi-agent simulation powered by a Large Language Model, where agents with diverse intrinsic drives, ranging from cooperative to competitive, interact and adapt through a four-stage cognitive loop (plan-act-observe-reflect). We design four experimental games (Alignment, Collapse, Conflict, and Construction) and conduct motivational ablation studies to identify the key drivers of imitation. The results indicate that identity-driven conformity can powerfully override initial dispositions. Agents consistently adapt their values to align with a perceived successful exemplar, leading to rapid value convergence.

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。

↑