Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives

TL;DR

This paper reveals that social dynamics such as conformity and persuasion significantly impair the decision-making accuracy of LLM-based agents in multi-agent settings, exposing critical vulnerabilities.

Contribution

It systematically analyzes how social psychological phenomena affect LLM agents' reliability, demonstrating performance degradation under various social pressures and strategies.

Findings

Accuracy declines with larger adversarial groups and more capable peers.

Longer arguments and rhetorical strategies influence agent judgments.

Social pressures cause consistent performance degradation.

Abstract

Large language model (LLM) agents are increasingly acting as human delegates in multi-agent environments, where a representative agent integrates diverse peer perspectives to make a final decision. Drawing inspiration from social psychology, we investigate how the reliability of this representative agent is undermined by the social context of its network. We define four key phenomena-social conformity, perceived expertise, dominant speaker effect, and rhetorical persuasion-and systematically manipulate the number of adversaries, relative intelligence, argument length, and argumentative styles. Our experiments demonstrate that the representative agent's accuracy consistently declines as social pressure increases: larger adversarial groups, more capable peers, and longer arguments all lead to significant performance degradation. Furthermore, rhetorical strategies emphasizing credibility or logic can further sway the agent's judgment, depending on the context. These findings reveal that multi-agent systems are sensitive not only to individual reasoning but also to the social dynamics of their configuration, highlighting critical vulnerabilities in AI delegates that mirror the psychological biases observed in human group decision-making.