Simulating Cooperative Prosocial Behavior with Multi-Agent LLMs: Evidence and Mechanisms for AI Agents to Inform Policy Decisions

TL;DR

This paper demonstrates that multi-agent LLM systems can simulate human prosocial behaviors, replicate complex experimental treatments, and exhibit real-world actions like collaboration and cheating, aiding policy development.

Contribution

It shows that multi-agent LLMs can accurately replicate human prosocial behavior and complex experimental conditions, advancing their use in policy simulation and analysis.

Findings

Successfully replicated human behavior in public goods game experiments

Can simulate combined experimental treatments not previously studied

Exhibit real-world actions like collaboration and cheating

Abstract

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.