# Simulating Cooperative Prosocial Behavior with Multi-Agent LLMs: Evidence and Mechanisms for AI Agents to Inform Policy Decisions arXiv: https://arxiv.org/abs/2502.12504 ยท HTML: https://mlsanity.com/paper/2502.12504/ ## Key facts - Cited by 20 papers in the map (data through 14 Oct 2026). - Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. - Builds on 8 of its 32 references that are in the map. - First posted on arXiv 18 Feb 2025. ## Placed in - LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/) ## Builds on (most cited first, 8 of 8) - [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023) - [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023) - [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022) - [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022) - [MetaAgents: Large Language Model Based Agents for Decision-Making on Teaming](https://mlsanity.com/paper/2310.06500/) (2023) - [Generative Agent-Based Modeling: Unveiling Social System Dynamics through Coupling Mechanistic Models with Generative Artificial Intelligence](https://mlsanity.com/paper/2309.11456/) (2023) - [The Good, the Bad, and the Hulk-like GPT: Analyzing Emotional Decisions of Large Language Models in Cooperation and Bargaining Games](https://mlsanity.com/paper/2406.03299/) (2024) - [Can Large Language Models Replace Human Subjects? A Large-Scale Replication of Scenario-Based Experiments in Psychology and Management](https://mlsanity.com/paper/2409.00128/) (2024) ## Built on by (most cited first, 20 of 20) - [OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation](https://mlsanity.com/paper/2506.05606/) (2025) - [Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shopping](https://mlsanity.com/paper/2510.07230/) (2025) - [LLM-Based Social Simulations Require a Boundary](https://mlsanity.com/paper/2506.19806/) (2025) - [When Is Collective Intelligence a Lottery? Multi-Agent Scaling Laws for Memetic Drift in LLMs](https://mlsanity.com/paper/2603.24676/) (2026) - [Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games](https://mlsanity.com/paper/2508.02076/) (2025) - [Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics](https://mlsanity.com/paper/2510.11290/) (2025) - [Arti-"fickle" Intelligence: Using LLMs as a Tool for Inference in the Political and Social Sciences](https://mlsanity.com/paper/2504.03822/) (2025) - [AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations](https://mlsanity.com/paper/2504.09662/) (2025) - [The AI in the Mirror: LLM Self-Recognition in an Iterated Public Goods Game](https://mlsanity.com/paper/2508.18467/) (2025) - [DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow](https://mlsanity.com/paper/2509.12626/) (2025) - [AdvisingWise: Supporting Academic Advising in Higher Education Settings Through a Human-in-the-Loop Multi-Agent Framework](https://mlsanity.com/paper/2511.05706/) (2025) - [Item-Mean Surrogates: Why Richer Persona Data Fail to Improve LLMs as Human Surrogates](https://mlsanity.com/paper/2608.29455/) (2026) - [Agent-Based Detection and Resolution of Incompleteness and Ambiguity in Interactions with Large Language Models](https://mlsanity.com/paper/2507.03726/) (2025) - [UBCL: A Reinforcement Learning Framework for Controllable and Diverse Player Behaviors](https://mlsanity.com/paper/2512.10835/) (2025) - [Language Model Agents Under Attack: A Cross Model-Benchmark of Profit-Seeking Behaviors in Customer Service](https://mlsanity.com/paper/2512.24415/) (2025) - [From Who They Are to How They Act: Behavioral Traits in Generative Agent-Based Models of Social Media](https://mlsanity.com/paper/2601.15114/) (2026) - [Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game](https://mlsanity.com/paper/2606.28456/) (2026) - [When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games](https://mlsanity.com/paper/2607.05132/) (2026) - [From Survey Personas to LLM Agents: A Generative Agent-based Simulation of Mobility Policy Preference Dynamics](https://mlsanity.com/paper/2608.07519/) (2026) - [AI Alignment through a Game-theoretic Lens: A Survey](https://mlsanity.com/paper/2608.27910/) (2026) ## Abstract (arXiv) Human prosocial cooperation is essential for our collective health, education, and welfare. However, designing social systems to maintain or incentivize prosocial behavior is challenging because people can act selfishly to maximize personal gain. This complex and unpredictable aspect of human behavior makes it difficult for policymakers to foresee the implications of their designs. Recently, multi-agent LLM systems have shown remarkable capabilities in simulating human-like behavior, and replicating some human lab experiments. This paper studies how well multi-agent systems can simulate prosocial human behavior, such as that seen in the public goods game (PGG), and whether multi-agent systems can exhibit ``unbounded actions'' seen outside the lab in real world scenarios. We find that multi-agent LLM systems successfully replicate human behavior from lab experiments of the public goods game with three experimental treatments - priming, transparency, and varying endowments. Beyond replicating existing experiments, we find that multi-agent LLM systems can replicate the expected human behavior when combining experimental treatments, even if no previous study combined those specific treatments. Lastly, we find that multi-agent systems can exhibit a rich set of unbounded actions that people do in the real world outside of the lab -- such as collaborating and even cheating. In sum, these studies are steps towards a future where LLMs can be used to inform policy decisions that encourage people to act in a prosocial manner.