titleMatrAIx: Simulating the World with 8.3 Billion Persona Agents
authorsXiaomin Li, Yuexing Hao, Jianheng Hou, Jintao Huang, Qianfeng Wen, Shirley Huang, Yifan Liu, Xiaoyi Liu, Yilan Fan, Yijun Wang, Koutian Wu, Ruoqi Gao, Muhammad Ahmed Mohsin, Jing Tang, Brihi Joshi, Heming Liu, Zheyuan Deng, Zonglin Di, Sankalp Jajee, Jiuyao Lu, Zhiwei Zhang, Saksham Kapoor, Ishan Gupta, Yunhan Zhao, Chanwoo Park, Yucheng Lu, Bing Hu, Weihang Xiao, Aravind Mohan, Hanwen Xing, Runyu Zhang, Mihir Kulshreshtha, Yuanda Xu, Qianyu Zhu, Dianzhuo Wang, Yuxin Xiao, Bowen Jiang, Yongye Su, Wenhao Chai, Zuxin Liu, Lawrence Yunliang Chen, Xuandong Zhao, Ethan Ye, Shivam Patel, Jason Xie, Alex Martin Richmond, Weixiang Ding, Emre Okcular, Diya Mathew, Ziheng Wang, Rana M. Shahroz Khan, Zhejian Peng, Fang Wu, Fan Nie, Xinyang Han, Yubin Kim, Jiawei Zhang, Zhenting Qi, Huangyuan Su, Xu Pan, Abinitha Gourabathina, Hyewon Jeong, Hemanth Neelgund Ramesh, Kumail Alhamoud, Kimia Hamidieh, Zidi Xiong, Samuel Schmidgall, Pengrui Han, Yepeng Huang, Yongheng Wang, Bowen Yang, Alex Gu, Yuchu Wang, Akshay Paruchuri, Brenna Li, Hejie Cui, Jiayuan Ding, Chaosheng Dong, Jiahao Wang, Yixuan He, Chi Wang, Pamela Bhattacharya, Tianyi Peng, Paul Pu Liang, Mitchell Gordon, Yilun Du, Marinka Zitnik, James Zou, Prasanna Tambe, Philip Torr, Emily Fox, Asu Ozdaglar, Dawn Song
date2026-08-04
venuearXiv (preprint, not peer reviewed)
idarXiv:2608.04205
affiliationMatrAIx
upvotes58 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf code
abstractHuman evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and interactive behavior. We therefore introduce MatrAIx, a population-scale simulated-user evaluation infrastructure for testing AI systems and digital products with heterogeneous users. MatrAIx has three core components: First, Persona 8B contains 8.3 billion persona records represented by 1,290 categorical dimensions. Records are either sampled from a dependency graph that preserves correlated attributes or derived from human-authored profiles. We release a quality-filtered coreset of approximately 1 million personas, comprising 599,847 human-grounded and 400,000 synthetic records. Second, the MatrAIx Playground provides four environments in which diverse users evaluate and interact with digital products: Survey, AI Chatbot, Web, and App. Third, MatrAIx provides 1,010 application tasks spanning more than 25 domains, including Commerce, Software, Finance, and Healthcare. We conducted 18,189 evaluation trials across eight representative tasks. Persona agents were powered by three LLMs: Claude Opus 4.8, GPT 5.5, and Claude Haiku 4.5. The resulting feedback captures how decisions and preferences vary across persona backgrounds, including hesitation after a price increase, willingness to continue after an AI assistant fails, and latency tolerance. We conducted two main validation studies: First, a 400-trial controlled study evaluated persona adherence across ten behavioral attributes and all four environments. The declared behavior was expressed or correctly suppressed in 366 trials (91.5%). Second, human and LLM judges evaluated the extraction quality of human-grounded personas. Overall, MatrAIx provides an end-to-end infrastructure for evaluating AI systems and digital products with diverse simulated human users.

cite

@misc{li2026matraix,
  title={MatrAIx: Simulating the World with 8.3 Billion Persona Agents},
  author={Xiaomin Li and Yuexing Hao and Jianheng Hou and Jintao Huang and Qianfeng Wen and Shirley Huang and Yifan Liu and Xiaoyi Liu and Yilan Fan and Yijun Wang and Koutian Wu and Ruoqi Gao and Muhammad Ahmed Mohsin and Jing Tang and Brihi Joshi and Heming Liu and Zheyuan Deng and Zonglin Di and Sankalp Jajee and Jiuyao Lu and Zhiwei Zhang and Saksham Kapoor and Ishan Gupta and Yunhan Zhao and Chanwoo Park and Yucheng Lu and Bing Hu and Weihang Xiao and Aravind Mohan and Hanwen Xing and Runyu Zhang and Mihir Kulshreshtha and Yuanda Xu and Qianyu Zhu and Dianzhuo Wang and Yuxin Xiao and Bowen Jiang and Yongye Su and Wenhao Chai and Zuxin Liu and Lawrence Yunliang Chen and Xuandong Zhao and Ethan Ye and Shivam Patel and Jason Xie and Alex Martin Richmond and Weixiang Ding and Emre Okcular and Diya Mathew and Ziheng Wang and Rana M. Shahroz Khan and Zhejian Peng and Fang Wu and Fan Nie and Xinyang Han and Yubin Kim and Jiawei Zhang and Zhenting Qi and Huangyuan Su and Xu Pan and Abinitha Gourabathina and Hyewon Jeong and Hemanth Neelgund Ramesh and Kumail Alhamoud and Kimia Hamidieh and Zidi Xiong and Samuel Schmidgall and Pengrui Han and Yepeng Huang and Yongheng Wang and Bowen Yang and Alex Gu and Yuchu Wang and Akshay Paruchuri and Brenna Li and Hejie Cui and Jiayuan Ding and Chaosheng Dong and Jiahao Wang and Yixuan He and Chi Wang and Pamela Bhattacharya and Tianyi Peng and Paul Pu Liang and Mitchell Gordon and Yilun Du and Marinka Zitnik and James Zou and Prasanna Tambe and Philip Torr and Emily Fox and Asu Ozdaglar and Dawn Song},
  year={2026},
  eprint={2608.04205},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2608.04205}
}