1
Will Scaling Improve Social Simulation with LLMs?
探讨LLM缩放能否提升社会模拟的保真度，揭示当前范式的局限与挑战
arXiv:2607.02464v1 Announce Type: new Abstract: Large Language Model (LLM) social simulations are a promising research method, but they are not yet fa…
2
Synthetic Personalities: How Well Can LLMs Mimic Individual Respondents Using Socio-Economic Microdata?
探究LLM基于社会经济微观数据模拟个体受访者的能力，揭示合成人格的逼真度与局限。
arXiv:2606.04592v1 Announce Type: cross Abstract: LLM-based digital twins promise to scale and accelerate market research, but most published twins ar…
3
Pimmur, can LLM simulate human collective behavior?
系统性审计39项研究，揭示LLM模拟人类集体行为的六类致命设计缺陷，AI社会实验的严谨性指南。
Article URL: https://arxiv.org/abs/2509.18052 Comments URL: https://news.ycombinator.com/item?id=48303461 Points: 1 # Comments: 0
4
How is agent society simulation going?
探讨AI Agent社会模拟领域三年来的突破性进展，来自Hacker News的讨论帖。
Three years past since Stanford Generative agents, is there any remarkable progress in this topic? Comments URL: https://news.ycombinator.com/item?id=…
5
Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits
微调提示词就能颠覆LLM社会模拟结论，稳健性审计刻不容缓。
arXiv:2605.18890v1 Announce Type: cross Abstract: The scientific claims drawn from LLM social simulations should be no stronger than the robustness au…
6
PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies
PAVE架构让AI代理学会在规则社会中“合法越轨”，模拟更真实的人类社会行为。
arXiv:2605.19351v1 Announce Type: cross Abstract: Generative agents based on large language models reproduce believable human behavior in cooperative …