Why Are We Moral? An LLM-based Agent Simulation Approach to Study Moral Evolution
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917438040309760 |
|---|---|
| author | Ziheng, Zhou Tang, Huacong Bi, Mingjie Kang, Yipeng He, Wanying Sun, Fang Sun, Yizhou Wu, Ying Nian Terzopoulos, Demetri Zhong, Fangwei |
| author_facet | Ziheng, Zhou Tang, Huacong Bi, Mingjie Kang, Yipeng He, Wanying Sun, Fang Sun, Yizhou Wu, Ying Nian Terzopoulos, Demetri Zhong, Fangwei |
| contents | The evolution of morality presents a puzzle: natural selection should favor self-interest, yet humans developed moral systems promoting altruism. Traditional approaches must abstract away cognitive processes, leaving open how cognitive factors shape moral evolution. We introduce an LLM-based agent simulation framework that brings cognitive realism to this question: agents with varying moral dispositions perceive, remember, reason, and decide in a simulated prehistoric hunter-gatherer society. This enables us to manipulate factors that traditional models cannot represent -- such as moral type observability and communication bandwidth -- and to discover emergent cognitive mechanisms from agent interactions. Across 20 runs spanning four settings, we find that cooperation and mutual help are the central driver of evolutionary survival, with universal and reciprocal morality exhibiting the most stable outcomes across conditions while selfishness is strongly disfavoured. Beyond cooperation itself, we further identify cognition as a central mediator -- most clearly through a cost of moral judgment that shifts the winning moral type across settings, with a self-purging effect among selfish agents as an additional cognitive pattern. We validate robustness across multiple LLM backbones, architecture ablations, and prompt sensitivity analyses. This work establishes LLM-based simulation as a powerful new paradigm to complement traditional research in evolutionary biology and anthropology, opening new avenues for investigating the complexities of moral and social evolution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17703 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Why Are We Moral? An LLM-based Agent Simulation Approach to Study Moral Evolution Ziheng, Zhou Tang, Huacong Bi, Mingjie Kang, Yipeng He, Wanying Sun, Fang Sun, Yizhou Wu, Ying Nian Terzopoulos, Demetri Zhong, Fangwei Multiagent Systems The evolution of morality presents a puzzle: natural selection should favor self-interest, yet humans developed moral systems promoting altruism. Traditional approaches must abstract away cognitive processes, leaving open how cognitive factors shape moral evolution. We introduce an LLM-based agent simulation framework that brings cognitive realism to this question: agents with varying moral dispositions perceive, remember, reason, and decide in a simulated prehistoric hunter-gatherer society. This enables us to manipulate factors that traditional models cannot represent -- such as moral type observability and communication bandwidth -- and to discover emergent cognitive mechanisms from agent interactions. Across 20 runs spanning four settings, we find that cooperation and mutual help are the central driver of evolutionary survival, with universal and reciprocal morality exhibiting the most stable outcomes across conditions while selfishness is strongly disfavoured. Beyond cooperation itself, we further identify cognition as a central mediator -- most clearly through a cost of moral judgment that shifts the winning moral type across settings, with a self-purging effect among selfish agents as an additional cognitive pattern. We validate robustness across multiple LLM backbones, architecture ablations, and prompt sensitivity analyses. This work establishes LLM-based simulation as a powerful new paradigm to complement traditional research in evolutionary biology and anthropology, opening new avenues for investigating the complexities of moral and social evolution. |
| title | Why Are We Moral? An LLM-based Agent Simulation Approach to Study Moral Evolution |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2509.17703 |