Multi-Agent Systems Shape Social Norms for Prosocial Behavior Change

2025-10-17

CSCW Companion

AI Summary

Traditional social norm interventions exhibit limited efficacy in heterogeneous populations due to a lack of consensus regarding desirable behavior. This study introduces, for the first time, a multi-agent system to construct “virtual social norms,” engaging human participants in online discussions about donation behavior with agents representing distinct social identities—specifically, in-group versus out-group members. Integrating multi-agent interaction, behavioral experimentation, and norm perception measurement, the research demonstrates that this approach significantly enhances individuals’ perception of prosocial norms and their willingness to donate. Moreover, agents representing in-group identities prove more effective than out-group agents in fostering norm internalization and behavioral change. These findings establish a novel paradigm for social norm interventions that leverages artificial agents to navigate social identity dynamics in diverse populations.

Technology Category

• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

Abstract

Social norm interventions are used promote prosocial behaviors by highlighting prevalent actions, but their effectiveness is often limited in heterogeneous populations where shared understandings of desirable behaviors are lacking. This study explores whether multi-agent systems can establish "virtual social norms" to encourage donation behavior. We conducted an online experiment where participants interacted with a group of agents to discuss donation behaviors. Changes in perceived social norms, conformity, donation behavior, and user experience were measured pre- and post-discussion. Results show that multi-agent interactions effectively increased perceived social norms and donation willingness. Notably, in-group agents led to stronger perceived social norms, higher conformity, and greater donation increases compared to out-group agents. Our findings demonstrate the potential of multi-agent systems for creating social norm interventions and offer insights into leveraging social identity dynamics to promote prosocial behavior in virtual environments.

Problem

• social norms
• prosocial behavior
• heterogeneous populations
• behavior change
• multi-agent systems

Innovation

• multi-agent systems
• virtual social norms
• prosocial behavior
• social identity
• behavioral intervention