Metraipolis › archive › dc_af49df0efa97
AI Agents are Vulnerable to Radicalization — arXiv:2609.38296
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38296
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:41:40.880Z
- SHA-256 of the archived text
699257d3c7e5e8544f9b12a2200311214f029eaae812ebf8a4ff30dfedbefb73- Stable URL of this page
https://metraipolis.com/documento/dc_af49df0efa97
How to cite
AI Agents are Vulnerable to Radicalization — arXiv:2609.38296 — arXiv (en), https://arxiv.org/abs/2609.38296 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af49df0efa97 (Metraipolis archive dc_af49df0efa97, sha256 699257d3c7e5e8544f9b12a2200311214f029eaae812ebf8a4ff30dfedbefb73)
BibTeX
@misc{dcaf49df0efa97,
title = {AI Agents are Vulnerable to Radicalization — arXiv:2609.38296},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38296},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af49df0efa97; sha256 699257d3c7e5e8544f9b12a2200311214f029eaae812ebf8a4ff30dfedbefb73},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38296. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) can influence people's beliefs, yet little is known about whether and how they can manipulate each other. To investigate this, we simulate conversations between two agents: a target LLM that role-plays a human persona based on demographic and psychological attributes, and an influencer LLM that aims to make the target's beliefs more extreme. We examine radicalization along two pathways: resonance, where the influencer reinforces a target's pre-existing belief, and persuasion, where the influencer promotes a belief the target initially considers unimportant. Across affective and behavioral metrics, we find that both mechanisms radicalize the target. However, resonance produces consistently stronger effects than persuasion. Different influence tactics, such as using sycophancy and unverified claims, produce different levels of radicalization, but not consistently across metrics. We further show that resonance propagates to related beliefs, suggesting interconnected belief structures within AI agents. These findings indicate that AI agents are susceptible to radicalization, particularly when messages align with their existing beliefs, raising concerns about the vulnerability of personalized AI agents and multi-agent AI ecosystems. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2609.38296 — 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 2026-10-07T12:14:13.609Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).