From Single to Societal: Analyzing Persona-Induced Bias in Multi-Agent Interactions

Large Language Model (LLM)-based multi-agent systems are increasingly used to simulate human interactions and solve collaborative tasks. A common practice is to assign agents with personas to encourage behavioral diversity. However, this raises a critical yet underexplored question: do personas introduce biases into multi-agent interactions? This paper presents a systematic investigation into persona-induced biases in multi-agent interactions, with a focus on social traits like trustworthiness (how an agent's opinion is received by others) and insistence (how strongly an agent advocates for its opinion). Through a series of controlled experiments in collaborative problem-solving and persuasion tasks, we reveal that (1) LLM-based agents exhibit biases in both trustworthiness and insistence, with personas from historically advantaged groups (e.g., men and White individuals) perceived as less trustworthy and demonstrating less insistence; and (2) agents exhibit significant in-group favoritism, showing a higher tendency to conform to others who share the same persona. These biases persist across various LLMs, group sizes, and numbers of interaction rounds, highlighting an urgent need for awareness and mitigation to ensure the fairness and reliability of multi-agent systems. Code - https://github.com/Jiayi-LizzZ/Persona-Induced- Bias-in-MAS.git Introduction With the rapid growth of Large Language Models (LLMs), LLM-based multi-agent systems have become a powerful paradigm for simulating human-like interactions and solving collaborative tasks (Guo et al. 2024; Mou et al. 2024) . By modeling intricate group behaviors and facilitating distributed decision-making, these systems become invaluable for enhancing the reasoning abilities of LLMs. A common practice in these systems is to equip each agent with distinct personas, such as demographic information, personality traits, and domain expertise, allowing them to exhibit diverse behaviors (Bhandari et al. 2025 ). However, while personas enrich agent behavior, they also introduce a critical concern: the potential for inducing bias.