# AI Agents are Vulnerable to Radicalization

arXiv: https://arxiv.org/abs/2609.38296 · HTML: https://mlsanity.com/paper/2609.38296/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 85 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 16 of 16)

- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Challenges in Detoxifying Language Models](https://mlsanity.com/paper/2109.07445/) (2021)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial](https://mlsanity.com/paper/2403.14380/) (2024)
- [MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate](https://mlsanity.com/paper/2406.14711/) (2024)
- ["Humans welcome to observe": A First Look at the Agent Social Network Moltbook](https://mlsanity.com/paper/2602.10127/) (2026)
- [Believe It or Not: How Deeply do LLMs Believe Implanted Facts?](https://mlsanity.com/paper/2510.17941/) (2025)
- [Social Influence and the Collective Dynamics of Opinion Formation](https://mlsanity.com/paper/1311.3475/) (2013)
- [Must Read: A Comprehensive Survey of Computational Persuasion](https://mlsanity.com/paper/2505.07775/) (2025)
- [AI, Help Me Thinkunicodex2014but for Myself: Assisting People in Complex Decision-Making by Providing Different Kinds of Cognitive Support](https://mlsanity.com/paper/2504.06771/) (2025)
- [Invisible Saboteurs: Sycophantic LLMs Mislead Novices in Problem-Solving Tasks](https://mlsanity.com/paper/2510.03667/) (2025)
- [Polarization of Autonomous Generative AI Agents Under Echo Chambers](https://mlsanity.com/paper/2402.12212/) (2024)
- [Deceptive AI systems that give explanations are more convincing than honest AI systems and can amplify belief in misinformation](https://mlsanity.com/paper/2408.00024/) (2024)

## Abstract (arXiv)

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.