Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

The Impact of Big Five Personality Traits on AI Agent Decision-Making in Public Spaces: A Social Simulation Study

Mingjun Ren, Wentao Xu

TL;DR

The study investigates how Big Five personality traits shape AI agent decision-making in public-space-like interactions using a classroom-based social simulation with ten trait-embedded agents, GPT-3.5-turbo, and the AgentVerse framework. It reveals that Openness to Experience most strongly drives information acceptance, with Extraversion and Conscientiousness also influencing decisions, while Neuroticism and Agreeableness yield more balanced effects; significant discrepancies between public expressions and private thoughts emerge for friendly and extroverted agents. These findings advance understanding of personality-driven behavior in AI agents operating in social contexts and highlight the need to account for environmental cues when designing context-aware systems. The work has practical implications for deploying AI agents in public-facing roles that must navigate misinformation and social dynamics.

Abstract

This study investigates how the Big Five personality traits influence decision-making processes in AI agents within public spaces. Using AgentVerse framework and GPT-3.5-turbo, we simulated interactions among 10 AI agents, each embodying different dimensions of the Big Five personality traits, in a classroom environment responding to misinformation. The experiment assessed both public expressions ([Speak]) and private thoughts ([Think]) of agents, revealing significant correlations between personality traits and decision-making patterns. Results demonstrate that Openness to Experience had the strongest impact on information acceptance, with curious agents showing high acceptance rates and cautious agents displaying strong skepticism. Extraversion and Conscientiousness also showed notable influence on decision-making, while Neuroticism and Agreeableness exhibited more balanced responses. Additionally, we observed significant discrepancies between public expressions and private thoughts, particularly in agents with friendly and extroverted personalities, suggesting that social context influences decision-making behavior. Our findings contribute to understanding how personality traits shape AI agent behavior in social settings and have implications for developing more nuanced and context-aware AI systems.

The Impact of Big Five Personality Traits on AI Agent Decision-Making in Public Spaces: A Social Simulation Study

TL;DR

The study investigates how Big Five personality traits shape AI agent decision-making in public-space-like interactions using a classroom-based social simulation with ten trait-embedded agents, GPT-3.5-turbo, and the AgentVerse framework. It reveals that Openness to Experience most strongly drives information acceptance, with Extraversion and Conscientiousness also influencing decisions, while Neuroticism and Agreeableness yield more balanced effects; significant discrepancies between public expressions and private thoughts emerge for friendly and extroverted agents. These findings advance understanding of personality-driven behavior in AI agents operating in social contexts and highlight the need to account for environmental cues when designing context-aware systems. The work has practical implications for deploying AI agents in public-facing roles that must navigate misinformation and social dynamics.

Abstract

This study investigates how the Big Five personality traits influence decision-making processes in AI agents within public spaces. Using AgentVerse framework and GPT-3.5-turbo, we simulated interactions among 10 AI agents, each embodying different dimensions of the Big Five personality traits, in a classroom environment responding to misinformation. The experiment assessed both public expressions ([Speak]) and private thoughts ([Think]) of agents, revealing significant correlations between personality traits and decision-making patterns. Results demonstrate that Openness to Experience had the strongest impact on information acceptance, with curious agents showing high acceptance rates and cautious agents displaying strong skepticism. Extraversion and Conscientiousness also showed notable influence on decision-making, while Neuroticism and Agreeableness exhibited more balanced responses. Additionally, we observed significant discrepancies between public expressions and private thoughts, particularly in agents with friendly and extroverted personalities, suggesting that social context influences decision-making behavior. Our findings contribute to understanding how personality traits shape AI agent behavior in social settings and have implications for developing more nuanced and context-aware AI systems.

Paper Structure

This paper contains 16 sections, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. The Big Five Personality Model in LLM Advancement
  4. Evaluation of Personality Traits in LLMs
  5. Generative Agents in Social Simulation
  6. Methodology
  7. Experimental Setup and Framework
  8. Agent Design and Personality Setting
  9. Public Space Simulation
  10. Misinformation Topics
  11. Personality Consistency Test
  12. Evaluation Metrics and Analysis
  13. Results
  14. Personality Trait Stability Analysis
  15. Personality Influences Decision-making
  16. ...and 1 more sections

Figures (2)

  • Figure 1: Visualization Interface of AgentVerse Framework: A Classroom-based Multi-agent Simulation Environment. The interface depicts a virtual classroom setting with a professor and multiple student agents, enabling real-time visualization of multi-agent interactions and dialogue exchanges.
  • Figure 2: Comparison of Expressed Opinions ([Speak]) and Internal Thoughts ([Think]) Across Ten Personality Types. The personality types are arranged in descending order based on the magnitude of discrepancy between expressed and internal responses. The discrepancy value indicates cognitive dissonance between expressed opinions and internal beliefs, where agents may express opinions ([Speak]) that differ from their internal judgments ([Think]), representing instances where public statements diverge from private beliefs.