Examining Agents' Bias Amplification versus Suppression in Multi-Agent Systems

• URL: http://arxiv.org/abs/2605.28098v1
• Date: Wed, 27 May 2026 07:53:29 GMT
• Title: Examining Agents' Bias Amplification versus Suppression in Multi-Agent Systems
• Abstract summary: We show that agents endowed with bias can substantially affect system-wide fairness.<n>When agents are exposed to bias uniformly, the system-wide bias elevates, even exceeding the additive sum of the individual agents' biases.
• Score: 5.210390383114933
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-agent systems are increasingly deployed to support various tasks where agents interact to achieve individual and collective objectives. Although these systems can enhance task performance and decision-making, fairness preservation through bias reduction remains challenging. This study examines how agent-level biases shift and impact system-wide fairness. We use prompts to expose individual agents to group-favoring bias, then assess downstream impacts at the system level. To quantify the impact, we propose Favor Bias Strength (FBS), a zero-centered metric that decomposes bias alteration between favored-group uplift and disfavored-group suppression. Using multiple agent designs, benchmarks, and up-to-date large language models, we show that agents endowed with bias can substantially affect system-wide fairness. Interestingly, when agents are exposed to bias uniformly, the system-wide bias elevates, even exceeding the additive sum of the individual agents' biases. The empirical evidence underscores the criticality of fairness in multi-agent systems, which warrants further analyses and empirical tests.

Related papers

• Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer? [31.047683581225087]
  We show that Friedkin-Johnsen (FJ) parameters are input-dependent, turning multi-agent deliberation into a mixture of experts.<n>We analyze how influence is established through observable proxies: agents' self-assessed confidence, their perceived confidence, and initial alignment with other agents' views.
  arXiv  Detail & Related papers  (2026-05-25T15:10:48Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• The Unfairness of Multifactorial Bias in Recommendation [68.35079031029616]
  Popularity bias and positivity bias are prominent sources of bias in recommender systems.<n>In this work, we examine how multifactorial bias influences item-side fairness.<n>We adapt a percentile-based rating transformation as a pre-processing strategy to mitigate multifactorial bias.
  arXiv  Detail & Related papers  (2026-01-19T08:37:43Z)
• Belief in Authority: Impact of Authority in Multi-Agent Evaluation Framework [3.6812160259693094]
  We present the first systematic analysis of role-based authority bias in free-form multi-agent evaluation using ChatEval.<n>Applying French and Raven's power-based theory, we classify authoritative roles into legitimate, referent, and expert types.<n>Experiments with GPT-4o and DeepSeek R1 reveal that Expert and Referent power roles exert stronger influence than Legitimate power roles.
  arXiv  Detail & Related papers  (2026-01-08T10:13:56Z)
• The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems [20.359327253718718]
  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.
  arXiv  Detail & Related papers  (2025-10-13T02:56:42Z)
• RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation [67.38036090822982]
  We propose RoboView-Bias, the first benchmark specifically designed to quantify visual bias in robotic manipulation.<n>We create 2,127 task instances that enable robust measurement of biases induced by individual visual factors and their interactions.<n>Our results highlight that systematic analysis of visual bias is a prerequisite for developing safe and reliable general-purpose embodied agents.
  arXiv  Detail & Related papers  (2025-09-26T13:53:25Z)
• Can an Individual Manipulate the Collective Decisions of Multi-Agents? [53.01767232004823]
  M-Spoiler is a framework that simulates agent interactions within a multi-agent system to generate adversarial samples.<n>M-Spoiler introduces a stubborn agent that actively aids in optimizing adversarial samples.<n>Our findings confirm the risks posed by the knowledge of an individual agent in multi-agent systems.
  arXiv  Detail & Related papers  (2025-09-20T01:54:20Z)
• 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)
• Mitigating Bias in RAG: Controlling the Embedder [26.799581301768622]
  We study the conflict between biases of each component and their relationship to the overall bias of the RAG system.<n>We show that bias conflict can be characterized through a linear relationship among components despite its complexity.<n>Our results underscore that a fair RAG system can be better achieved by carefully controlling the bias of the embedder rather than increasing its fairness.
  arXiv  Detail & Related papers  (2025-02-24T18:16:10Z)
• Statistical discrimination in learning agents [64.78141757063142]
  Statistical discrimination emerges in agent policies as a function of both the bias in the training population and of agent architecture. We show that less discrimination emerges with agents that use recurrent neural networks, and when their training environment has less bias.
  arXiv  Detail & Related papers  (2021-10-21T18:28:57Z)

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.