Yutong Xie

I am a Ph.D. candidate and a Barbour Scholar at the University of Michigan School of Information, advised by Prof. Qiaozhu Mei. Prior to this, I received my Bachelor’s degree from Shanghai Jiao Tong University as a member of the ACM Class, advised by Prof. Yong Yu and Prof. Weinan Zhang.

Email: yutxie AT umich DOT edu
Links: Google Scholar, LinkedIn, Twitter, Github, CV

Jump to: RESEARCH / PUBLICATIONS / BIO

RESEARCH

My research lies in AI Behavioral Science, with three core directions:

Assessing and guiding AI behavior using tools from behavioral science [PNAS’24, AIBS’24];
Simulating and interpreting human behavior with AI [PNAS’25, Social Sim’25];
Analyzing and fostering human-AI collaboration as well as their coevolution.

I also develop behavioral foundation models (Be.FM), which aim to provide a shared scientific representation of behavior across humans and AI. Further details and community discussions about this emerging field can be found in our perspective paper and recent workshops.

More broadly, I have a general interest in AI for Science [NAACL’25, ICLR’23, ICLR’21] and AI for Creativity [WWW’23].

I am searching for academic jobs that start from Fall 2026! If my research aligns with your interest or you know of any relevant opportunities, I would be more than happy to get in touch :). Please find my CV here.

NEW! I will be attending the Rising Stars in EECS Workshop at MIT on Oct 30-31! Happy to connect :)
NEW! Our paper on using LLMs to decipher human behaviors is now published in PNAS!
NEW! Our behavioral foundation models (Be.FM) are reported by UofM News!
CFP! We just launched a new research topic of AI Behavioral Science in the Frontiers in AI journal! Look forward to your contributions and let’s build the conversation together! (Submission deadline Sep 29, 2025)

SELECTED PUBLICATIONS

AI Behavioral Science / AI for Science / Other Topics

For all publications, please visit my Google Scholar page.

AI Behavioral Science

Using large language models to categorize strategic situations and decipher motivations behind human behaviors
Yutong Xie, Qiaozhu Mei, Walter Yuan, Matthew O. Jackson.
Proceedings of the National Academy of Sciences of the United States of America (PNAS), 2025.
[PDF] [arXiv] [SSRN] [Code] [Slides]
Be.FM: Open Foundation Models for Human Behavior
Yutong Xie^*, Zhuoheng Li^*, Xiyuan Wang^*, Yijun Pan, Qijia Liu, Xingzhi Cui, Kuang-Yu Lo, Ruoyi Gao, Xingjian Zhang, Jin Huang, Walter Yuan, Matthew O. Jackson, Qiaozhu Mei.
[PDF] [arXiv] [SSRN] [Hugging Face] [Access Request] [UMich News]
A Turing test of whether AI chatbots are behaviorally similar to humans
Qiaozhu Mei, Yutong Xie, Walter Yuan, Matthew O. Jackson.
Proceedings of the National Academy of Sciences of the United States of America (PNAS), 2024.
[PDF] [arXiv] [SSRN] [Code] [Slides] [UMich News] [Stanford News] [Swarma Club] [Follow-up Study]
AI Behavioral Science (perspective paper)
Matthew O. Jackson, Qiaozhu Mei, Stephanie Wang, Yutong Xie, Walter Yuan, Seth G. Benzell, Erik Brynjolfsson, Colin Camerer, James A. Evans, Brian Jabarian, Jon Kleinberg, Juanjuan Meng, Sendhil Mullainathan, Asuman E. Ozdaglar, Thomas Pfeiffer, Moshe Tennenholtz, Robb Willer, Diyi Yang, Teng Ye.
Manuscript in submission.
[SSRN]

AI for Science (AI4Science)

Bridging AI and Science: Implications from a Large-Scale Literature Analysis of AI4Science
Yutong Xie^*, Yijun Pan^*, Hua Xu, Qiaozhu Mei.
Manuscript in submission.
[PDF] [arXiv] [Code]
MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows
Xingjian Zhang^*, Yutong Xie^*, Jin Huang, Jinge Ma, Zhaoying Pan, Qijia Liu, Ziyang Xiong, Tolga Ergen, Dongsub Shim, Honglak Lee, Qiaozhu Mei.
Findings of the Association for Computational Linguistics (NAACL), 2025.
[PDF] [arXiv] [Code] [HuggingFace]
How Much Space Has Been Explored? Measuring the Chemical Space Covered by Databases and Machine-Generated Molecules
Yutong Xie, Ziqiao Xu, Jiaqi Ma, Qiaozhu Mei.
International Conference on Learning Representations (ICLR), 2023.
[PDF] [arXiv] [Code] [SlidesLive] [Slides] [Poster] [AI Time Talk]
MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
Yutong Xie, Chence Shi, Hao Zhou, Yuwei Yang, Weinan Zhang, Yong Yu, Lei Li.
International Conference on Learning Representations (ICLR), 2021 (Spotlight presentation ).
[PDF] [arXiv] [Code] [SlidesLive] [Slides] [Poster] [AI Time Talk] [WeChat Article]

We also created a short video showing the evolution of AI and data mining over half a century (1969-2022), which is featured by KDD 2023. Come take a look :).