Multi-Agents are Social Groups: Investigating Social Influence of Multiple Agents in Human-Agent Interactions

TL;DR

This paper explores how groups of AI agents can exert social influence on humans, showing that multiple agents can increase social pressure and shift opinions more effectively than single agents in human-agent interactions.

Contribution

It demonstrates that multi-agent systems can create stronger social influence on humans, highlighting their potential for positive social impact and manipulation.

Findings

Multiple agents increase social pressure on users.

Conversations with multiple agents cause greater opinion shifts.

Multi-agent systems outperform single-agent systems in influencing opinions.

Abstract

Multi-agent systems - systems with multiple independent AI agents working together to achieve a common goal - are becoming increasingly prevalent in daily life. Drawing inspiration from the phenomenon of human group social influence, we investigate whether a group of AI agents can create social pressure on users to agree with them, potentially changing their stance on a topic. We conducted a study in which participants discussed social issues with either a single or multiple AI agents, and where the agents either agreed or disagreed with the user's stance on the topic. We found that conversing with multiple agents (holding conversation content constant) increased the social pressure felt by participants, and caused a greater shift in opinion towards the agents' stances on each topic. Our study shows the potential advantages of multi-agent systems over single-agent platforms in causing opinion change. We discuss design implications for possible multi-agent systems that promote social good, as well as the potential for malicious actors to use these systems to manipulate public opinion.