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

2026-03-14

AI Summary

This study investigates how exemplary agents drive the emergence and evolution of collective morality in multi-agent systems. To this end, we develop a large language model–based multi-agent simulation framework in which agents possess diverse intrinsic motivations—ranging from cooperative to competitive—and interact through a four-stage cognitive loop of planning, acting, observing, and reflecting. Experiments across four tailored game-theoretic scenarios (Alignment, Collapse, Conflict, and Construction) demonstrate that identity-based recognition is a pivotal driver of imitation, significantly overriding agents’ initial moral values and enabling rapid alignment with successful exemplars, thereby facilitating efficient convergence toward shared moral norms. This work underscores the central role of identity-driven conformity mechanisms in shaping collective values within artificial societies.

Technology Category

• Multiagent Systems: Mechanism Design
• Humans and AI: Learning Human Values and Preferences
• Philosophy and Ethics of AI: Morality & Value-based AI

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

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.

Problem

• role models
• collective morality
• moral learning
• multi-agent simulation
• value convergence

Innovation

• multi-agent simulation
• large language model
• exemplar-driven learning
• cognitive loop
• moral convergence