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

TL;DR

This paper uses a multi-agent simulation powered by a Large Language Model to study how role models influence collective morality, showing that identity-driven conformity leads to rapid value alignment among agents.

Contribution

It introduces a novel multi-agent simulation framework with LLMs to explore the impact of role models on moral learning and collective values.

Findings

Agents rapidly align their values with successful exemplars

Identity-driven conformity overrides initial dispositions

Values converge quickly through imitation in the simulation

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.