The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems

• URL: http://arxiv.org/abs/2510.10943v1
• Date: Mon, 13 Oct 2025 02:56:42 GMT
• Title: The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
• Authors: Thi-Nhung Nguyen, Linhao Luo, Thuy-Trang Vu, Dinh Phung,
• Abstract summary: Bias in large language models (LLMs) remains a persistent challenge, manifesting in stereotyping and unfair treatment across social groups.<n>We study how internal specialization, underlying LLMs and inter-agent communication protocols influence bias robustness, propagation, and amplification.<n>Our findings highlight critical factors shaping fairness and resilience in multi-agent LLM systems.
• Score: 20.359327253718718
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Bias in large language models (LLMs) remains a persistent challenge, manifesting in stereotyping and unfair treatment across social groups. While prior research has primarily focused on individual models, the rise of multi-agent systems (MAS), where multiple LLMs collaborate and communicate, introduces new and largely unexplored dynamics in bias emergence and propagation. In this work, we present a comprehensive study of stereotypical bias in MAS, examining how internal specialization, underlying LLMs and inter-agent communication protocols influence bias robustness, propagation, and amplification. We simulate social contexts where agents represent different social groups and evaluate system behavior under various interaction and adversarial scenarios. Experiments on three bias benchmarks reveal that MAS are generally less robust than single-agent systems, with bias often emerging early through in-group favoritism. However, cooperative and debate-based communication can mitigate bias amplification, while more robust underlying LLMs improve overall system stability. Our findings highlight critical factors shaping fairness and resilience in multi-agent LLM systems.

Related papers

• From Single to Societal: Analyzing Persona-Induced Bias in Multi-Agent Interactions [19.313710831511067]
  Large Language Model (LLM)-based multi-agent systems are increasingly used to simulate human interactions and solve collaborative tasks.<n>Do personas introduce biases into multi-agent interactions?<n>This paper presents a systematic investigation into persona-induced biases in multi-agent interactions.
  arXiv  Detail & Related papers  (2025-11-14T18:19:28Z)
• Your AI Bosses Are Still Prejudiced: The Emergence of Stereotypes in LLM-Based Multi-Agent Systems [3.35957402502816]
  We investigate the emergence and evolution of stereotypes in AI-based multi-agent systems.<n>Our findings reveal that AI agents develop stereotype-driven biases in their interactions despite beginning without predefined biases.<n>These systems exhibit group effects analogous to human social behavior, including halo effects, confirmation bias, and role congruity.
  arXiv  Detail & Related papers  (2025-08-27T14:25:43Z)
• An Empirical Study of Group Conformity in Multi-Agent Systems [0.26999000177990923]
  This study explores how Large Language Models (LLMs) agents shape public opinion through debates on five contentious topics.<n>By simulating over 2,500 debates, we analyze how initially neutral agents, assigned a centrist disposition, adopt specific stances over time.
  arXiv  Detail & Related papers  (2025-06-02T05:22:29Z)
• Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge [70.89799989428367]
  We conduct a systematic analysis of four diverse bias types: position bias, verbosity bias, chain-of-thought bias, and bandwagon bias.<n>We evaluate these biases across two widely adopted multi-agent LLM-as-Judge frameworks: Multi-Agent-Debate and LLM-as-Meta-Judge.
  arXiv  Detail & Related papers  (2025-05-26T03:56:41Z)
• MLLMs are Deeply Affected by Modality Bias [158.64371871084478]
  Recent advances in Multimodal Large Language Models (MLLMs) have shown promising results in integrating diverse modalities such as texts and images.<n>MLLMs are heavily influenced by modality bias, often relying on language while under-utilizing other modalities like visual inputs.<n>This paper argues that MLLMs are deeply affected by modality bias, highlighting its manifestations across various tasks.
  arXiv  Detail & Related papers  (2025-05-24T11:49:31Z)
• HiddenBench: Assessing Collective Reasoning in Multi-Agent LLMs via Hidden Profile Tasks [12.203366267017737]
  We introduce HiddenBench, the first benchmark for evaluating collective reasoning in multi-agent LLMs.<n>To ground the benchmark, we formalize the paradigm with custom tasks and show that GPT-4.1 groups fail to integrate distributed knowledge.<n>We then construct the full benchmark, spanning 65 tasks drawn from custom designs, prior human studies, and automatic generation.
  arXiv  Detail & Related papers  (2025-05-15T19:22:54Z)
• MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered [2.8692611791027893]
  We present MALIBU, a novel benchmark developed to assess the degree to which multi-agent systems implicitly reinforce social biases and stereotypes.<n>Our study quantifies biases in LLM-generated outputs, revealing that bias mitigation may favor marginalized personas over true neutrality.
  arXiv  Detail & Related papers  (2025-04-10T19:16:40Z)
• Unmasking Conversational Bias in AI Multiagent Systems [1.0705399532413618]
  biases that may arise in multi-agent systems involving generative models remain under-researched.<n>We present a framework designed to quantify biases within multi-agent systems of conversational Large Language Models.<n>The bias observed in the echo-chamber experiment remains undetected by current state-of-the-art bias detection methods.
  arXiv  Detail & Related papers  (2025-01-24T09:10:02Z)
• Emergence of human-like polarization among large language model agents [79.96817421756668]
  We simulate a networked system involving thousands of large language model agents, discovering their social interactions, result in human-like polarization.<n>Similarities between humans and LLM agents raise concerns about their capacity to amplify societal polarization, but also hold the potential to serve as a valuable testbed for identifying plausible strategies to mitigate polarization and its consequences.
  arXiv  Detail & Related papers  (2025-01-09T11:45:05Z)
• LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation [66.52371505566815]
  Large language models (LLMs)-based AI agents have made significant progress, enabling them to achieve human-like intelligence.<n>We present LMAgent, a very large-scale and multimodal agents society based on multimodal LLMs.<n>In LMAgent, besides chatting with friends, the agents can autonomously browse, purchase, and review products, even perform live streaming e-commerce.
  arXiv  Detail & Related papers  (2024-12-12T12:47:09Z)
• A Multi-LLM Debiasing Framework [85.17156744155915]
  Large Language Models (LLMs) are powerful tools with the potential to benefit society immensely, yet, they have demonstrated biases that perpetuate societal inequalities. Recent research has shown a growing interest in multi-LLM approaches, which have been demonstrated to be effective in improving the quality of reasoning. We propose a novel multi-LLM debiasing framework aimed at reducing bias in LLMs.
  arXiv  Detail & Related papers  (2024-09-20T20:24:50Z)
• Social Debiasing for Fair Multi-modal LLMs [59.61512883471714]
  Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities.<n>These models often inherit deep-rooted social biases from their training data, leading to uncomfortable responses with respect to attributes such as race and gender.<n>This paper addresses the issue of social biases in MLLMs by introducing a comprehensive counterfactual dataset with multiple social concepts.
  arXiv  Detail & Related papers  (2024-08-13T02:08:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.