两篇新研究论文探讨了大型语言模型 (LLM) 代理在模拟社会中的行为。第一篇论文《LLM 代理社会中涌现的关系秩序》提出了一个名为 CAREB-MAS 的多代理框架，该框架可重现劳动专业化和权威分层等社会现象。第二篇论文《涌现共识何时真实？》介绍了一种测量协议和诊断工具，用于区分 LLM 代理社会中真实的社会动态和模型伪影，发现 LLM 不会自发地自我极化，并且共识可能是模型伪影。 AI
影响 这些研究强调了需要鲁棒的方法来分析 LLM 代理行为，并区分真实的社会动态和模型伪影，这对于开发可靠的 AI 系统至关重要。
排序理由 两篇在 arXiv 上发表的学术论文，讨论了 LLM 代理社会和涌现行为。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.23764v1 Announce Type: cross Abstract: Fei Xiaotong's Differential Order Pattern characterizes rural society as egocentric and relationally graded, with cooperation attenuating over social distance. Although often treated as culturally specific, its mechanistic basis r…
Fei Xiaotong's Differential Order Pattern characterizes rural society as egocentric and relationally graded, with cooperation attenuating over social distance. Although often treated as culturally specific, its mechanistic basis remains under-operationalized, and prior LLM-based …
LLM "agent societies" are studied via demonstrations of emergent consensus or polarization -- with no measurable control parameter, no theory of when each regime appears, and no test of whether an outcome is a genuine social dynamic or a model artifact. We introduce the coupling …