Norms are known to be a major factor determining humans behavior. It's also shown that norms can be quite effective tool for building agent-based societies. Various normative architectures have been proposed for designing normative multi-agent systems (NorMAS). Due to human nature of the concept norms, many of these architectures are built based on theories in social sciences. Tipping point theory, as is briefly discussed in this paper, seems to have a great potential to be used for designing normative architectures. This theory deals with the factors that affect social epidemics that arise in human societies. In this paper, we try to apply the main concepts of this theory to agent-based normative architectures. We show several ways to implement these concepts, and study their effects in an agent-based normative scenario.
Emergence of Social Norms in Generative Agent Societies: Principles and Architecture
School of Mechanical Engineering, Northwestern Polytechnical University（西北工业大学机械工程学院）；School of Cybersecurity, Northwestern Polytechnical University（西北工业大学网络空间安全学院）；School of Artificial Intelligence, OPtics and ElectroNics(iOPEN), Northwestern Polytechnical University（西北工业大学人工智能、光学与电子学院（iOPEN））；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Few self-involved agents among BC agents can lead to polarized local or global consensus
社会问题通常由高度参与和较少参与的人讨论，以建立社会规范，定义必须思考和做些什么。由于自我参与的代理人分享不同的态度动态其他代理伍德，池等，1996年，我们研究了规范的出现和演变，通过一个基于个人的模型，涉及这两种类型的代理人。自我参与主体的动力学来自Huet and Deffuant，2010，其他主体的动力学来自Deffuant et al，2001。智能体的态度被表示为一个连续的态度空间上的一段。如果两个智能体的态度段有足够的重叠，则它们是接近的。我们的代理人讨论两个不同的问题，其中一个，称为主要问题，是更重要的自我参与的代理人比其他，称为次要问题。自我参与的代理人被吸引在这两个问题上，如果他们是接近的主要问题，但转移远离他们的同行的意见，如果他们只是接近次要问题。显然，非自我参与的代理人被其他代理人吸引时，他们都接近的主要和次要问题。我们观察到各种类型的极端小集群的出现。在一组或不同的态度中，它们可能导致已经建立的温和规范或在次要和/或主要问题上两极分化的规范。他们还可以推动聚集在不同群体中的持不同意见的代理人达成全球温和的共识。
