1
哈佛大学和麻省理工造出 83 亿个“AI 人”，模拟全球人类行为
83亿个AI人模拟全球人类行为，哈佛MIT联手OpenAI和DeepMind，91.5%准确率震惊学界。
IT之家 8 月 18 日消息，由哈佛大学和麻省理工学院牵头，OpenAI 和谷歌 DeepMind 等机构参与的团队在本月推出了 MatrAIx 系统 。 该系统能够生成 83 亿个 AI 智能体 ，用于模拟全球人类行为。 该项目利用 1,290 个维度对不同背景和生活方式的人群进行建模。这些 A…
2
Show HN: Axiom-02 – Deterministic engine modeling cognitive dissonance
用确定性引擎模拟高压下的认知失调与冲突决策，开源可玩，适合AI与心理学交叉爱好者。
Article URL: https://github.com/Zierax/Axiom-02 Comments URL: https://news.ycombinator.com/item?id=48835555 Points: 1 # Comments: 0
3
LLM-based Human Simulations Have Not Yet Been Reliable
顶级AI学者论文直指：基于大语言模型的人类模拟仍不可靠，结论值得关注。
arXiv:2501.08579v3 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diver…
4
Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call
让AI模拟学习者行为更省数据？这个教育代理框架通过点名机制实现高效仿真，教育科技研究的新利器。
arXiv:2606.15225v1 Announce Type: cross Abstract: Large-scale learner-task interaction data are crucial for intelligent educational systems but are co…
5
Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents
用户稍不耐烦就崩溃？研究揭示AI智能体脆弱性，呼吁高仿真人类特质测试以提升鲁棒性。
arXiv:2510.04491v3 Announce Type: replace Abstract: Despite rapid progress in building conversational AI agents, robustness is still largely untested.…
6
Teaching Values to Machines: Simulating Human-Like Behavior in LLMs
心理学理论赋能大模型，诱导LLM展现类人价值行为，探索AI对齐新路径
arXiv:2605.30036v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate a remarkable capacity to adopt different personas and roles; …
7
Reinforcing Human Behavior Simulation via Verbal Feedback
用语言反馈教大模型模拟人类行为，比代码数学更难但更具社会智能价值
arXiv:2605.20506v1 Announce Type: new Abstract: Humans learn social norms and behaviors from verbal feedback (e.g., a parent saying "that was rude" or…