Elamur Research⌕
☰
home / papers / 2026 / Why Are We Moral? An LLM-based Agent Simulation Approach to the Study of Moral Evolution

Why Are We Moral? An LLM-based Agent Simulation Approach to the Study of Moral Evolution

Paper · 2026 · Zhou Ziheng, Huacong Tang, Mingjie Bi et al.

Summary

The paper asks why moral behaviour could evolve when natural selection seems to reward self-interest. Classical tools such as evolutionary game theory reduce agents to fixed strategies or payoff tables. As a result, they cannot show how cognition (memory, reasoning, recognising others' dispositions, communicating) affects which moral systems persist. The authors instead build LLM-driven agents that live in a simulated prehistoric hunter-gatherer world. These agents perceive, remember, reflect and decide according to an assigned moral disposition, and the dispositions are based on Singer's "expanding circle" theory. The researchers vary factors that traditional models cannot represent, including how visible an agent's moral type is and how costly communication is. They then track which types survive and reproduce. Over 20 runs in four settings, cooperation and mutual aid were the main drivers of survival. Universal and reciprocal morality produced the most stable outcomes, while selfishness was strongly selected against. The work positions LLM-based simulation as a complement to evolutionary biology and anthropology. It also releases reusable tools for studying social evolution.

Key points

  • The authors release two tools: MoRE, a morality-driven cognitive agent architecture with a reflection step, and Social-Evol, an extensible environment for long-term and scenario-based social simulation.
  • Agents are assigned one of four moral types along the expanding circle:
    • self-focused, which reproduce but give no offspring care (modelled on r-selected species);
    • kin-focused;
    • reciprocal group-focused;
    • universal group-focused.
  • The experiments covered 20 runs across four settings. Robustness was checked with several LLM backbones, architecture ablations and prompt-sensitivity tests.
  • Two mechanisms emerged from agent cognition:
    • Cost of moral judgment: assessing others' trustworthiness is time-consuming and error-prone. Unconditional cooperators gain a reputation quickly and avoid this cost.
    • Self-purging: selfish agents tend to eliminate one another.
  • When communication is prohibitively costly, selfish agents can outcompete moral ones.
  • Stated limitations include weak spatial and temporal reasoning in the LLMs, no model of sexual selection, and a restriction to hunter-gatherer conditions.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of California, Los AngelesLos Angeles · United States99 works · 56,333 citations🎓Beijing Normal UniversityBeijing · China22 works · 3,177 citations🏛️Beijing Institute for General Artificial IntelligenceBeijing · China11 works · 633 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksSocial Sciences · 1,954 worksSociology and Political Science · 626 worksNeuroscience · 186 worksCognitive Neuroscience · 185 works

Cite

Cite as Zhou Ziheng, Huacong Tang, Mingjie Bi, Wanying He, Fang Sun, Yizhou Sun, Ying Nian Wu, Demetri Terzopoulos, Yipeng Kang and Fangwei Zhong. 2026. Why Are We Moral? An LLM-based Agent Simulation Approach to the Study of Moral Evolution. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.1339

@inproceedings{ziheng2026why,
  title = {{Why Are We Moral? An LLM-based Agent Simulation Approach to the Study of Moral Evolution}},
  author = {Zhou Ziheng, Huacong Tang, Mingjie Bi, Wanying He, Fang Sun, Yizhou Sun, Ying Nian Wu, Demetri Terzopoulos, Yipeng Kang and Fangwei Zhong},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1339},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1339}
}

References

48 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Gati Aher, Rosa I Arriaga, and Adam Tauman Kalai. 2023. Using large language models to simulate multiple humans and replicate human subject studies. arXiv preprint arXiv:2306.07872. find
  2. Solomon E Asch. 1946. Forming impressions of personality. The Journal of Abnormal and Social Psychology, 41(3):258. find
  3. Robert Axelrod and William D Hamilton. 1981. The evolution of cooperation. Science, 211(4489):1390– 1396. find
  4. Albert Bandura. 1977. Social learning theory. Prentice Hall. find
  5. Paul Bloom. 2013. Just babies: The origins of good and evil. Crown. find
  6. Samuel Bowles and Herbert Gintis. 2004. The evolution of strong reciprocity: cooperation in heterogeneous populations. Theoretical population biology, 65(1):17–28. find
  7. Robert Boyd, Peter J Richerson, and Joseph Henrich. 2011. The cultural niche: Why social learning is essential for human adaptation. Proceedings of the National Academy of Sciences, 108(Supplement 2):10918–10925. find
  8. Oliver Scott Curry, Daniel A Mullins, and Harvey Whitehouse. 2019a. Is it good to cooperate? testing the theory of morality-as-cooperation in 60 societies. Current Anthropology, 60(1):47–69. find
  9. Oliver Scott Curry, Daniel Austin Mullins, and Harvey Whitehouse. 2019b. Is it good to cooperate? testing the theory of morality-as-cooperation in 60 societies. Current Anthropology, 60(1):47–69. find
  10. Gordon Dai, Weijia Zhang, Jinhan Li, Siqi Yang, Srihas Rao, Arthur Caetano, Misha Sra, and 1 others. 2024. Artificial leviathan: Exploring social evolution of llm agents through the lens of hobbesian social contract theory. arXiv preprint arXiv:2406.14373. — [arXiv:2406.14373](https://arxiv.org/abs/2406.14373) find
  11. Richard Dawkins. 1976. The selfish gene. Oxford University Press. find
  12. Morton Deutsch. 1973. The resolution of conflict: Constructive and destructive processes. Yale University Press. find
  13. Ernst Fehr and Simon Gächter. 2002. Altruistic punishment in humans. Nature, 415(6868):137–140. find
  14. Hsiao-Tung Fei. 1992. From the Soil, the Foundations of Chinese Society. University of California Press, Berkeley. Translated by Gary G. Hamilton and Wang Zheng. find
  15. Alan P Fiske. 1992. The four elementary forms of sociality: framework for a unified theory of social relations. Psychological Review, 99(4):689–723. find
  16. Carol Gilligan. 1982. In a different voice: Psychological theory and women’s development. Harvard University Press. find
  17. Zhenyu Guan, Xiangyu Kong, Fangwei Zhong, and Yizhou Wang. 2024. Richelieu: Self-evolving llm-based agents for ai diplomacy. Advances in Neural Information Processing Systems, 37:123471–123497. find
  18. Jonathan Haidt. 2001. The emotional dog and its rational tail: a social intuitionist approach to moral judgment. Psychological review, 108(4):814. find
  19. Jonathan Haidt. 2007. The new synthesis in moral psychology. Science, 316(5827):998–1002. find
  20. Jonathan Haidt and Craig Joseph. 2007. The moral mind: How 5 sets of innate moral intuitions guide the development of many culture-specific virtues, and perhaps even modules. In Peter Carruthers, Stephen Laurence, and Stephen Stich, editors, The innate mind: Volume 3: Foundations and the future, pag… find
  21. William D Hamilton. 1964. The genetical evolution of social behaviour. i. Journal of theoretical biology, 7(1):1–16. find
  22. J Kiley Hamlin, Karen Wynn, and Paul Bloom. 2011. Young infants prefer prosocial to antisocial others. Cognitive Development, 26(1):30–39. find
  23. Joseph Henrich. 2015. The secret of our success: How culture is driving human evolution, domesticating our species, and making us smarter. Princeton University Press. find
  24. Clare Janaki Holden and Ruth Mace. 2003. Spread of cattle led to the loss of matrilineal descent in africa: a coevolutionary analysis. Proceedings of the Royal Society of London. Series B: Biological Sciences, 270(1532):2425–2433. find
  25. John J Horton. 2023. Large language models as simulated economic agents: What can we learn from homo silicus? arXiv preprint arXiv:2301.07543. — [arXiv:2301.07543](https://arxiv.org/abs/2301.07543) find
  26. Yizhe Huang, Xingbo Wang, Hao Liu, Fanqi Kong, Aoyang Qin, Min Tang, Xiaoxi Wang, Song-Chun Zhu, Mingjie Bi, Siyuan Qi, and 1 others. 2024. Adasociety: An adaptive environment with social structures for multi-agent decision-making. Advances in Neural Information Processing Systems, 37:35388–35413. find
  27. Herbert Gintis, Eric Alden Smith, and Samuel Bowles. 2001. Costly signaling and cooperation. Journal of theoretical biology, 213(1):103–119. find
  28. Hillard Kaplan, Kim Hill, Jane Lancaster, and A Magdalena Hurtado. 1992. The evolution of life history theory: A bibliometric study of an interdisciplinary research area. Evolutionary Anthropology: Issues, News, and Reviews, 1(2):62–71. find
  29. Kurt Gray, Liane Young, and Adam Waytz. 2012. Moral judgment is not a moral science. Psychological Review, 119(3):542–572. find
  30. James Konow. 2003. Which is the fairest one of all? a positive analysis of justice theories. Journal of Economic Literature, 41(4):1188–1239. find
  31. Joshua D Greene. 2013. Moral tribes: Emotion, reason, and the gap between us and them. Penguin. find
  32. Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. Camel: Communicative agents for" mind" exploration of large language model society. Advances in Neural Information Processing Systems, 36:51991–52008.
  33. Mart R Gross. 2005. The evolution of parental care. The Quarterly Review of Biology, 80(1):37–45. find
  34. Siobhán M Mattison, Eric Alden Smith, Mary K Shenk, and Ethan E Cochrane. 2011. The evolutionary ecology of despotism. Evolution and Human Behavior, 32(5):334–347. find
  35. Martin A Nowak. 2006. Five rules for the evolution of cooperation. Science, 314(5805):1560–1563. find
  36. Michael Tomasello. 2016. A natural history of human morality. Harvard University Press. find
  37. Robert L Trivers. 1971. The evolution of reciprocal altruism. The Quarterly Review of Biology, 46(1):35– 57. find
  38. Martin A Nowak and Karl Sigmund. 1998. The dynamics of indirect reciprocity. Journal of theoretical biology, 194(4):561–574. find
  39. Stephen T Trumbo. 2012. Patterns of parental care in invertebrates. In Nick J Royle, Per T Smiseth, and Mathias Kölliker, editors, Evolution of Parental Care, pages 81–100. Oxford University Press, Oxford. find
  40. Martin A Nowak and Karl Sigmund. 2005. Evolution of indirect reciprocity. Nature, 437(7063):1291–1298. find
  41. Elliot Turiel. 1983. The development of social knowledge: Morality and convention. Cambridge University Press. find
  42. Joon Sung Park, Joseph C O’Brien, Carrie J Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–22. find
  43. Eric R Pianka. 1970. On r and k selection. The American Naturalist, 104(940):592–597. find
  44. Yiding Wang, Yuxuan Chen, Fangwei Zhong, Long Ma, and Yizhou Wang. 2024. Simulating human-like daily activities with desire-driven autonomy. arXiv preprint arXiv:2412.06435. — [arXiv:2412.06435](https://arxiv.org/abs/2412.06435) find
  45. Zhilin Wang, Yu Ying Chiu, and Yu Cheung Chiu. 2023. Humanoid agents: Platform for simulating human-like generative agents. arXiv preprint arXiv:2310.05418. find
  46. Jinghua Piao, Yuwei Yan, Jun Zhang, Nian Li, Junbo Yan, Xiaochong Lan, Zhihong Lu, Zhiheng Zheng, Jing Yi Wang, Di Zhou, and 1 others. 2025. Agentso-ciety: Large-scale simulation of llm-driven generative agents advances understanding of human behaviors and society. arXiv preprint arXiv:2502.08691. — [arXiv:2502.08691](https://arxiv.org/abs/2502.08691) find
  47. Felix Warneken and Michael Tomasello. 2006. Altruistic helping in human infants and young chimpanzees. Science, 311(5765):1301–1303. find
  48. Tage S Rai and Alan P Fiske. 2011. Moral psychology is relationship regulation: moral motives for unity, hierarchy, equality, and proportionality. Psychological Review, 118(1):57–75. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ziheng-2026-why-are-we-moral-llm/