Metraipolis › archive › dc_7ed04544819f

Homogenization in Multi-Agent Systems — arXiv:2610.09824

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.09824
License (as archived): CC0-1.0
Archived: 2026-10-08T12:35:51.636Z
SHA-256 of the archived text: 4147205018b19dfea0540de3e9389c3af18026a1e7d1599ab08713c8aa79ec6f
Stable URL of this page: https://metraipolis.com/documento/dc_7ed04544819f

How to cite

Homogenization in Multi-Agent Systems — arXiv:2610.09824 — arXiv (en), https://arxiv.org/abs/2610.09824 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ed04544819f (Metraipolis archive dc_7ed04544819f, sha256 4147205018b19dfea0540de3e9389c3af18026a1e7d1599ab08713c8aa79ec6f)

BibTeX

@misc{dc7ed04544819f,
  title = {Homogenization in Multi-Agent Systems — arXiv:2610.09824},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09824},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ed04544819f; sha256 4147205018b19dfea0540de3e9389c3af18026a1e7d1599ab08713c8aa79ec6f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09824. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.09824 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:14:15.278Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).