Metraipolis › archive › dc_d8014fff0cb3
When Extremists Enter LLM Societies: Investigating Extreme Behavior in Multi-Agent Systems — arXiv:2610.19863
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19863
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T13:50:40.063Z
- SHA-256 of the archived text
c10a5244a93028e4dc1e3909b9f5bcc0743dfda57dce6dcbde08b298432da65b- Stable URL of this page
https://metraipolis.com/documento/dc_d8014fff0cb3
How to cite
When Extremists Enter LLM Societies: Investigating Extreme Behavior in Multi-Agent Systems — arXiv:2610.19863 — arXiv (en), https://arxiv.org/abs/2610.19863 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d8014fff0cb3 (Metraipolis archive dc_d8014fff0cb3, sha256 c10a5244a93028e4dc1e3909b9f5bcc0743dfda57dce6dcbde08b298432da65b)
BibTeX
@misc{dcd8014fff0cb3,
title = {When Extremists Enter LLM Societies: Investigating Extreme Behavior in Multi-Agent Systems — arXiv:2610.19863},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19863},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d8014fff0cb3; sha256 c10a5244a93028e4dc1e3909b9f5bcc0743dfda57dce6dcbde08b298432da65b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19863. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model (LLM) agents increasingly serve as computational actors in multi-agent social simulations. While existing work emphasizes representative personas and average-case behavior, social science shows that persistent tail actors can disproportionately shape collective dynamics. We study this regularity in controlled LLM-based multi-agent systems (LLM-MAS). In these systems, such actors cannot be reduced to fixed scalar states: prompts, natural-language histories, and backbone generation mediate their behavior and influence. We first analyzed three properties of extremists in sociology and model the LLM extremist based on LLM-native perspective. We introduce EXAM, an EXtremist Agent Modeling framework that capable of configuring extremist agents for specific tasks and precisely controlling their population proportion, spatial distribution, interaction protocols, and measurement interfaces. Across four scenarios: congressional election, financial crisis, epidemic public opinion, and iterated prisoner's dilemma, we observe that small persistent tail groups produce measurable, backbone- and scenario-dependent collective shifts. EXAM shows how this social-science regularity manifests through language-mediated mechanisms specific to LLM-based social simulation. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2610.19863 — 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 2026-10-15T13:48:35.440Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).