# Homogenization in Multi-Agent Systems

arXiv: https://arxiv.org/abs/2610.09824 · HTML: https://mlsanity.com/paper/2610.09824/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 16 of its 55 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 16 of 16)

- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Is Temperature the Creativity Parameter of Large Language Models?](https://mlsanity.com/paper/2405.00492/) (2024)
- [A Survey of AI Agent Protocols](https://mlsanity.com/paper/2504.16736/) (2025)
- [AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation](https://mlsanity.com/paper/2312.13010/) (2023)
- [The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process](https://mlsanity.com/paper/2506.01080/) (2025)
- [Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems](https://mlsanity.com/paper/2602.15198/) (2026)
- [AI-Assisted Peer Review at Scale: The AAAI-26 AI Review Pilot](https://mlsanity.com/paper/2604.13940/) (2026)
- [ReviewerToo: Should AI Join The Program Committee? A Look At The Future of Peer Review](https://mlsanity.com/paper/2510.08867/) (2025)
- [Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework](https://mlsanity.com/paper/2509.21267/) (2025)
- [Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents](https://mlsanity.com/paper/2608.16578/) (2026)
- [Emergent Bias and Fairness in Multi-Agent Decision Systems](https://mlsanity.com/paper/2512.16433/) (2025)
- [MASCA: LLM based-Multi Agents System for Credit Assessment](https://mlsanity.com/paper/2507.22758/) (2025)
- [Small Changes, Big Impact: Demographic Bias in LLM-Based Hiring Through Subtle Sociocultural Markers in Anonymised Resumes](https://mlsanity.com/paper/2603.05189/) (2026)
- [ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review](https://mlsanity.com/paper/2601.22638/) (2026)
- [LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review](https://mlsanity.com/paper/2604.16321/) (2026)
- [Evaluating Language Models on Cross-Language Code Functional Equivalence](https://mlsanity.com/paper/2608.23961/) (2026)

## Abstract (arXiv)

Multi-agent systems (MAS) leverage interactions between agents to perform complex tasks. Despite their success, we show that these interactions can also lead to homogenization, i.e., agents converging to similar behaviors. Homogenization in MAS can reduce agent diversity and reinforce shared failures. In this paper, we operationalize homogenization using three metrics: conformity to the majority, polarization towards extremes, and growing inertia against changes over subsequent interactions. We evaluate homogenization in MAS for code generation, hiring, and scientific peer review. Across these tasks, we show that homogenization translates to concrete downstream risks: in code generation, it hides and amplifies correlated errors which can create systemic vulnerabilities; in hiring, it allows the influence of biased agents to persist long after their removal; and in peer review, it creates uneven evaluation standards across research areas. Our results establish homogenization as a failure mode of MAS, demonstrating that MAS evaluations must move beyond aggregate performance to carefully analyze interaction dynamics. Finally, we show that simple approaches to increase diversity---leveraging sampling stochasticity and mixed-models MAS---fail to reduce homogenization risks, highlighting the need for strategies to effectively leverage agent diversity.