Emergent Discrimination and Polarization in Multi-Agent Systems

DOI10.48550/ARXIV.2610.22701MaRDI QIDQ7395323arXivFDO

Authors Nestor Caticha, Davi Bastos Costa, Otavio Citton, Renato Vicente, João Henrique Sant'Ana, Felippe Alves, Mariana Mercucci, Juan P. Neirotti

Publication date 15 October 2026

Published in arXiv

Tldr This work studies theoretically how discrimination and polarization emerge in populations of learning agents. Through simulations with large language models, we identify four collective states and show that simple local learning dynamics can generate qualitatively distinct forms of polarization and discrimination depending on the strength and prevalence of group bias.

Full work available at URL https://doi.org/10.48550/ARXIV.2610.22701

arXiv classification

cond-mat.dis-nn cs.MA physics.soc-ph

This page was built for publication: Emergent Discrimination and Polarization in Multi-Agent Systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7395323)