Investigating Moral Evolution Via LLM-Based Agent Simulation

Zhou Ziheng, Huacong Tang, Mingjie Bi, Ying Nian Wu, Demetri Terzopoulos, Fangwei Zhong

Keywords: morality, evolution, society, simulation, competition, collaboration

TL;DR: an llm-agent based simulation approach to study why morality evolves

Abstract: The evolution of morality presents a puzzle: natural selection should favor self-interest, yet humans developed moral systems promoting cooperation. We introduce an LLM-based agent simulation framework modeling prehistoric hunter-gatherer societies with agents of varying moral dispositions based on expanding circles of concern. The framework demonstrates how moral dispositions interact with environmental pressures and cognitive constraints to produce different evolutionary outcomes. Our approach offers four key contributions: methodologically, it enables psychologically realistic evolutionary simulations; theoretically, it reveals the critical role of cognitive factors in moral evolution; empirically, it provides evidence for how different moral orientations succeed under varying conditions; and programmatically, it establishes an extensible simulation framework for investigating diverse social evolutionary questions. This work establishes a novel complementary paradigm to traditional evolutionary biology and anthropological research for investigating complex social evolution.

Submission Number: 11