LLM多智能体系统中的临界点：气候变化行动立场
原标题：Tipping Points in LLM-Based Multi-Agent Systems: Stance on Climate Change Action
AI 摘要
该研究利用LLM驱动的基于智能体的建模（ABM）构建了一个微型社会，探讨气候变化行动立场的社会临界点。智能体的立场由气候行动紧迫性的信念强度和机构信任度两个变量定义，通过多轮对话监测智能体间距离和LDA主题模式来量化信念变化。研究发现该简单模型中确实会出现气候立场的显著突变，同时报告了LLM偏见干扰对话动态、需要维护智能体人格和情景记忆等方法论教训。
正文节选
Tipping Points in LLM-Based Multi-Agent Systems: Stance on Climate Change Action Abstract Because significant action to counter global warming requires massive public support, it is important to understand the dynamics of public opinion on climate issues. Of special interest are social tipping points, as revealed by large-scale effects of small perturbations in individual behaviors. Agent-based models (ABM) are an effective computational tool for studying these matters, because they allow contro