Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.28098 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914607253159936 |
|---|---|
| author | Wu, Zejian Eric Jiang, Zhongyi Zhuang, Yuan Hu, Paul Jen-Hwa |
| author_facet | Wu, Zejian Eric Jiang, Zhongyi Zhuang, Yuan Hu, Paul Jen-Hwa |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28098 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Examining Agents' Bias Amplification versus Suppression in Multi-Agent Systems Wu, Zejian Eric Jiang, Zhongyi Zhuang, Yuan Hu, Paul Jen-Hwa Artificial Intelligence 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. |
| title | Examining Agents' Bias Amplification versus Suppression in Multi-Agent Systems |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.28098 |