Metraipolis › archive › dc_bd27ebdb1ea3

Emergent Discrimination and Polarization in Multi-Agent Systems — arXiv:2610.22701

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.22701
License (as archived): CC0-1.0
Archived: 2026-10-19T08:38:43.065Z
SHA-256 of the archived text: 9a392b01946f783ff0e8f31c50db8a386865160634d4af6fee7b867def51d3b3
Stable URL of this page: https://metraipolis.com/documento/dc_bd27ebdb1ea3

How to cite

Emergent Discrimination and Polarization in Multi-Agent Systems — arXiv:2610.22701 — arXiv (en), https://arxiv.org/abs/2610.22701 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd27ebdb1ea3 (Metraipolis archive dc_bd27ebdb1ea3, sha256 9a392b01946f783ff0e8f31c50db8a386865160634d4af6fee7b867def51d3b3)

BibTeX

@misc{dcbd27ebdb1ea3,
  title = {Emergent Discrimination and Polarization in Multi-Agent Systems — arXiv:2610.22701},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22701},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd27ebdb1ea3; sha256 9a392b01946f783ff0e8f31c50db8a386865160634d4af6fee7b867def51d3b3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22701. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study theoretically how discrimination and polarization can emerge in a population of learning agents. Each agent uses an adaptive linear decision layer to map a language-model embedding of an issue to a binary opinion and maintains an evolving estimate of how much it trusts every other agent. Through pairwise interactions, agents update both their decision weights and trust estimates using an online Bayesian rule derived from teacher-student learning over a noisy channel. In-context-learning experiments with large language models qualitatively reproduce the predicted opinion and trust updates. We then assign each agent one of two arbitrary group labels, A or B, and model group bias by allowing a fraction $f_b$ of agents to shift its perceived agreement with each message by a strength $b$, a bias steering prejudice, depending on whether the sender and receiver share a label. We use order parameters from statistical mechanics to connect these local dynamics to collective states and transitions. Starting from uniformly random initial conditions, simulations reveal a rich phase diagram in the $(b,f_b)$ plane, comprising four collective states: spin-glass frustrated out-group favoritism, nondiscriminatory polarization, discrimination with opinion alignment, and discrimination without opinion alignment. Which state emerges depends on both the strength and prevalence of the bias. These results show how simple local learning dynamics can generate qualitatively distinct forms of polarization and discrimination, underscoring the need for population-level safety analysis of multi-agent systems. They also suggest measurable order parameters for characterizing analogous collective states in human societies.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Disordered Systems and Neural Networks (cond-mat.dis-nn); Physics and Society (physics.soc-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.22701 — 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 2026-10-19T08:38:39.950Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).