Background - 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.
Our Work - We conducted a study in which participants (n=94) 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.
Findings - We found that conversing with multiple agents increased the social pressure felt by participants, and caused a greater shift in opinion towards the agents' stances on the conversation topics. Our study shows the potential advantages of multi-agent systems over single-agent platforms in causing opinion change.
Implication - We discuss the resulting possibilities for multi-agent systems that promote social good, as well as potential malicious actors using these systems to manipulate public opinion.
🔗 Link