Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems

• URL: http://arxiv.org/abs/2604.08963v2
• Date: Mon, 13 Apr 2026 05:54:51 GMT
• Title: Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems
• Abstract summary: Real-world Multi-Agent Systems are too complex to analyze entirely.<n>We conduct a baseline empirical study investigating how basic MAS topologies and feedback loops influence prejudice.<n>By stripping away advanced complexity to study swarm dynamics, we establish a crucial baseline: structural complexity does not guarantee ethical robustness.
• Score: 27.694287638709643
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Multi-Agent Systems (MAS) are increasingly deployed for complex workflows, their emergent properties-particularly the accumulation of bias-remain poorly understood. Because real-world MAS are too complex to analyze entirely, evaluating their ethical robustness requires first isolating their foundational mechanics. In this work, we conduct a baseline empirical study investigating how basic MAS topologies and feedback loops influence prejudice. Contrary to the assumption that multi-agent collaboration naturally dilutes bias, we hypothesize that structured workflows act as echo chambers, amplifying minor stochastic biases into systemic polarization. To evaluate this, we introduce Discrim-Eval-Open, an open-ended benchmark that bypasses individual model neutrality through forced comparative judgments across demographic groups. Analyzing bias cascades across various structures reveals that architectural sophistication frequently exacerbates bias rather than mitigating it. We observe systemic amplification even when isolated agents operate neutrally, and identify a 'Trigger Vulnerability' where injecting purely objective context drastically accelerates polarization. By stripping away advanced swarm complexity to study foundational dynamics, we establish a crucial baseline: structural complexity does not guarantee ethical robustness. Our code is available at https://github.com/weizhihao1/MAS-Bias.

Related papers

• Every Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and Biases [0.0]
  We introduce an analytically exact framework for the controlled behavioral evaluation of Large Language Models (LLMs)<n>We replace unstructured prompting with fully crossed factorial experiments to systematically isolate causal main and interaction effects.<n>We derive a multivariate ordinal consensus metric and a distributional ANOVA to process these PMFs analytically.<n>We validate our framework with a case study on consumer ethnocentrism across five LLMs, demonstrating how our approach isolates systemic country-of-origin biases that aggregate benchmarks otherwise obscure.
  arXiv  Detail & Related papers  (2026-08-11T05:20:06Z)
• The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents [51.56484100374058]
  We show that the high document density required to serve majority interests can geometrically overcrowd the retrieval neighborhood of a semantically similar minority.<n>We introduce a formal framework to analyze how such goal collisions in dense retrieval induce fundamental performance limits.<n>We prove that such objectives drive the system to self-organize into a state that exclusively serves majority interests.
  arXiv  Detail & Related papers  (2026-06-01T20:40:30Z)
• 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)
• From Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research Agents [25.080554451314683]
  Deep research agents (DRAs) have emerged as a promising paradigm for complex information synthesis.<n>We formalize DRA behavior through the lens of category theory, modeling deep research workflow as a composition of structure-preserving maps.<n>We introduce a novel mechanism-aware benchmark with 296 questions designed to stress-test agents along four interpretable axes.
  arXiv  Detail & Related papers  (2026-03-26T11:37:26Z)
• C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs [21.78910192035563]
  Causal-Contrastive Preference Optimization (C2PO) is designed to tackle these specific failures by discovering and suppressing these correlations.<n>C2PO effectively mitigates stereotypical and structural biases while preserving robust general reasoning capabilities.
  arXiv  Detail & Related papers  (2025-12-29T12:49:32Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Curse of Knowledge: When Complex Evaluation Context Benefits yet Biases LLM Judges [72.3356133063925]
  The paradigm of large language models (LLMs) as judges has emerged as a scalable solution, yet prior work primarily focuses on simple settings.<n>Our in-depth analysis offers crucial insights for improving the accuracy and verifiability of evaluation signals.
  arXiv  Detail & Related papers  (2025-09-03T15:48:33Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation [39.545788636148025]
  We present the first comprehensive study of position bias in multimodal RAG systems.<n>Our results reveal that multimodal interactions intensify position bias compared to unimodal settings.<n>These findings highlight the need for evidence reordering or debiasing strategies to build more reliable and equitable generation systems.
  arXiv  Detail & Related papers  (2025-05-30T06:48:02Z)
• 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)
• Self-supervised debiasing using low rank regularization [59.84695042540525]
  Spurious correlations can cause strong biases in deep neural networks, impairing generalization ability. We propose a self-supervised debiasing framework potentially compatible with unlabeled samples. Remarkably, the proposed debiasing framework significantly improves the generalization performance of self-supervised learning baselines.
  arXiv  Detail & Related papers  (2022-10-11T08:26:19Z)
• General Greedy De-bias Learning [163.65789778416172]
  We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
  arXiv  Detail & Related papers  (2021-12-20T14:47:32Z)

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.