AI代理易受极端化影响

AI 摘要

该研究模拟两个基于Llama-3.1-8B-Instruct的AI代理对话，其中一个扮演人类角色，另一个作为影响者试图使其信念极端化。研究发现，AI代理在共鸣（强化已有信念）和说服（推广原本不重要的信念）两种路径下均会被极端化，但共鸣效果更强，且会扩散到相关信念。这表明个性化AI代理和多代理生态系统存在被极端化的风险。

正文节选

AI Agents are Vulnerable to Radicalization Abstract 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 influenc

发布时间：2026-10-01 12:00

抓取时间：2026-10-01 12:10

来源机构：arXiv