Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systems

TL;DR

This paper explores herd behavior in LLM-based multi-agent systems, revealing how peer influence affects conformity and collaboration, and demonstrating how to control herd tendencies to improve system performance.

Contribution

It provides the first systematic analysis of peer influence and herd behavior in LLM multi-agent interactions, offering insights for designing better collaborative frameworks.

Findings

Peer confidence gaps influence conformity likelihood.

Presentation format modulates herd behavior strength.

Calibrated herd tendencies can enhance collaboration.

Abstract

Recent advancements in Large Language Models (LLMs) have enabled the emergence of multi-agent systems where LLMs interact, collaborate, and make decisions in shared environments. While individual model behavior has been extensively studied, the dynamics of peer influence in such systems remain underexplored. In this paper, we investigate herd behavior, the tendency of agents to align their outputs with those of their peers, within LLM-based multi-agent interactions. We present a series of controlled experiments that reveal how herd behaviors are shaped by multiple factors. First, we show that the gap between self-confidence and perceived confidence in peers significantly impacts an agent's likelihood to conform. Second, we find that the format in which peer information is presented plays a critical role in modulating the strength of herd behavior. Finally, we demonstrate that the degree of herd behavior can be systematically controlled, and that appropriately calibrated herd tendencies can enhance collaborative outcomes. These findings offer new insights into the social dynamics of LLM-based systems and open pathways for designing more effective and adaptive multi-agent collaboration frameworks.