English(EN) When Extremists Enter LLM Societies: Investigating Extreme Behavior in Multi-Agent Systems

新框架模拟大语言模型社会中极端智能体的影响

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-14 09:27

研究人员开发了 EXAM（EXtremist Agent Modeling）框架，旨在研究大型语言模型（LLM）驱动的多智能体系统中持久性边缘参与者的影响。该框架允许在模拟中配置极端智能体，控制其比例、分布和交互协议。在国会选举、金融危机、疫情公众舆论和迭代囚徒困境这四种场景下的研究表明，即使是少数极端智能体也能显著影响集体动态，其影响取决于大语言模型骨干和具体场景。 AI

影响这项研究可能带来更真实的社会动态模拟，从而增进对复杂人工智能系统中涌现行为的理解。

排序理由该条目是一篇学术论文，详细介绍了模拟多智能体系统中极端行为的新框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.MA (Multiagent) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目是一篇学术论文，详细介绍了模拟多智能体系统中极端行为的新框架。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.MA (Multiagent) TIER_1 English(EN) · Junjie Huang · 2026-10-14 09:27

当极端分子进入大型语言模型社会：多智能体系统中的极端行为调查

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 collecti…

本文如何被排名

报道来源 [1]

当极端分子进入大型语言模型社会：多智能体系统中的极端行为调查

相关实体

相关话题