An LLM-based Agent Simulation Approach to Study Moral Evolution

2025-09-22

AI Summary

Natural selection favors self-interest, yet humans evolved altruism-oriented moral systems—a central puzzle in evolutionary ethics. Method: This paper introduces a novel agent-based simulation paradigm leveraging large language models (LLMs) as cognitively constrained, morally inclined agents within a simulated hunter-gatherer society. The framework integrates the expanding circles theory with group dynamics and conducts iterative moral evolution experiments. Contribution/Results: It is the first work to deploy LLMs as embodied moral agents driving evolutionary processes and to jointly model moral frameworks with cognitive constraints. Results demonstrate that their interaction critically shapes the emergence pathways of altruistic behavior; moreover, simulated outcomes align closely with classical theories—including kin selection and reciprocal altruism—thereby establishing the first computationally tractable, reproducible, and empirically verifiable social-scientific simulation platform for studying moral evolution.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Philosophy and Ethics of AI: Morality & Value-based AI
• Humans and AI: Learning Human Values and Preferences

Application Category

• 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
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The evolution of morality presents a puzzle: natural selection should favor self-interest, yet humans developed moral systems promoting altruism. We address this question by introducing a novel Large Language Model (LLM)-based agent simulation framework modeling prehistoric hunter-gatherer societies. This platform is designed to probe diverse questions in social evolution, from survival advantages to inter-group dynamics. To investigate moral evolution, we designed agents with varying moral dispositions based on the Expanding Circle Theory citep{singer1981expanding}. We evaluated their evolutionary success across a series of simulations and analyzed their decision-making in specially designed moral dilemmas. These experiments reveal how an agent's moral framework, in combination with its cognitive constraints, directly shapes its behavior and determines its evolutionary outcome. Crucially, the emergent patterns echo seminal theories from related domains of social science, providing external validation for the simulations. 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.

Problem

• Modeling moral evolution puzzle using LLM-based agent simulations
• Investigating how moral dispositions affect evolutionary success in societies
• Analyzing agent decision-making in moral dilemmas with cognitive constraints

Innovation

• LLM-based agent simulation for moral evolution
• Agents designed with Expanding Circle Theory
• Analyzing moral dilemmas and evolutionary outcomes