# Emergent Bias and Fairness in Multi-Agent Decision Systems

arXiv: https://arxiv.org/abs/2512.16433 · HTML: https://mlsanity.com/paper/2512.16433/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication](https://mlsanity.com/paper/2312.01823/) (2023)
- [Large Language Model Agent in Financial Trading: A Survey](https://mlsanity.com/paper/2408.06361/) (2024)
- [Voting or Consensus? Decision-Making in Multi-Agent Debate](https://mlsanity.com/paper/2502.19130/) (2025)
- [Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions](https://mlsanity.com/paper/2410.02584/) (2024)
- [TABLET: Learning From Instructions For Tabular Data](https://mlsanity.com/paper/2304.13188/) (2023)
- [ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration](https://mlsanity.com/paper/2411.00053/) (2024)
- [Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications](https://mlsanity.com/paper/2310.14607/) (2023)
- [Enhancing Financial Question Answering with a Multi-Agent Reflection Framework](https://mlsanity.com/paper/2410.21741/) (2024)
- [FinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis](https://mlsanity.com/paper/2509.17395/) (2025)

## Built on by (most cited first, 5 of 5)

- [AgentFairBench: Do LLM Agents Discriminate When They Act?](https://mlsanity.com/paper/2606.16723/) (2026)
- [Beyond Arrow's Impossibility: Fairness as an Emergent Property of Multi-Agent Collaboration](https://mlsanity.com/paper/2604.13705/) (2026)
- [Examining Agents' Bias Amplification versus Suppression in Multi-Agent Systems](https://mlsanity.com/paper/2605.28098/) (2026)
- [Compliant with Local Controls, Collectively Discriminatory. A Governance Architecture for Multi-Agent AI in Regulated Finance](https://mlsanity.com/paper/2609.27994/) (2026)
- [Homogenization in Multi-Agent Systems](https://mlsanity.com/paper/2610.09824/) (2026)

## Abstract (arXiv)

Multi-agent systems have demonstrated the ability to improve performance on a variety of predictive tasks by leveraging collaborative decision making. However, the lack of effective evaluation methodologies has made it difficult to estimate the risk of bias, making deployment of such systems unsafe in high stakes domains such as consumer finance, where biased decisions can translate directly into regulatory breaches and financial loss. To address this challenge, we need to develop fairness evaluation methodologies for multi-agent predictive systems and measure the fairness characteristics of these systems in the financial tabular domain. Examining fairness metrics using large-scale simulations across diverse multi-agent configurations, with varying communication and collaboration mechanisms, we reveal patterns of emergent bias in financial decision-making that cannot be traced to individual agent components, indicating that multi-agent systems may exhibit genuinely collective behaviors. Our findings highlight that fairness risks in financial multi-agent systems represent a significant component of model risk, with tangible impacts on tasks such as credit scoring and income estimation. We advocate that multi-agent decision systems must be evaluated as holistic entities rather than through reductionist analyses of their constituent components.