Iām a Ph.D. student in Cognitive Science in Education at Columbia University. My research centers on responsible and human-centered AI in education.
Specifically, I draw on perspectives from cognitive science, psychology, learning science, and assessment approaches in the social sciences to pursue two complementary goals: understanding how AI is reshaping human cognition, decision-making, and interaction, and developing methods to evaluate and improve existing AI systems for more effective and reliable use.
Iāve been fortunate to be advised by Professor Renzhe Yu at Columbia University. Previously, I received my masterās degree from Beijing Normal University in STEM Education, where I was advised by Professor Ping Zhang.
Recently, my research has focused on three main areas:
- AI and the Transformation of Higher Education. I study the broader impact of AI on learnersā cognitive engagement, social interaction, and the skills and competencies emphasized in higher education through large-scale behavioral and interaction log analysis.
- AI as a Cognitive Partner and Pedagogical Assistant. I develop the evaluation framework to assess the pedagogical capabilities of AI systems, and draw on learning sciences theory to design AI agents that can better support complex learning.
- Evaluation Paradigms for Human-AI Collaboration Tasks. I investigate evaluation methods for human-AI collaboration tasks, with the goal of moving beyond simple accuracy-based metrics toward more reliable and explainable assessment paradigms.
š¢ News
- 2026.03 ā Our LAK 2026 paper received a Best Full Paper nomination!
- 2026.02 ā I will co-organize the LAK 2026 workshop āCurriculum Analytics for 21st-Century Competencies in Postsecondary Educationā in Bergen, Norway
- 2025.07 ā I will attend AIED, EDM, and L@S in July 2025 in Perlamo, Italy. Happy to connect if you'll be there too!
- 2025.04 ā I will give an online talk as a Guest Speaker and Panelist at the Educational Technology Sub-Forum of the 16th China Education Symposium at Harvard University.
- 2025.03 ā I will give an online talk as a Guest Speaker at the AI Application Sub-Forum of Columbia University Teachers College China-US Education Forum.
- 2024.11 ā Our paper āIntersectional inequalities in asynchronous academic communicationā won Best Student Paper Awards at SCiP 2024š.
- 2024.09 ā I will start my PhD in Cognitive Science at Teachers College, Columbia University!
š” Selected Publications
Please check my Google Scholar profile for a full list of publications.
Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning. [link]
Zhiyuan Hu, Yunhai Hu, Juncheng Liu, Shuyue Stella Li, Yucheng Wang, Zhen Xu et al.
arXiv preprint arXiv:2601.09667 (Under review: ACL 2026)
Enhancing LLM-Based Data Annotation with Error Decomposition. [link]
Zhen Xu, Vedant Khatri, Yijun Dai, Xiner Liu, Siyan Li, Xuanming Zhang, Renzhe Yu.
The 16th International Learning Analytics & Knowledge Conference (LAK), 2026 š Best Full Paper Nomination
Evaluating 21st-Century Competencies in Higher Education Curricula with Large Language Models: Benchmarking and Targeted Prompting Strategies. [link]
Zhen Xu, Xin Guan, Chenxi Shi, Qinhao Chen, Renzhe Yu.
Journal of Learning Analytics, 1ā24, 2026
Bringing Pedagogy into Focus: Evaluating Virtual Teaching Assistants in Asynchronous Learning Environments. [link]
ā Siyan Li, ā Zhen Xu, Vethavikashini Chithrra Raghuram, Xuanming Zhang, Renzhe Yu, Zhou Yu.
Findings of the Association for Computational Linguistics: (EMNLP Findings), 2025
From Course to Skill: Evaluating LLM Performance in Curricular Analytics. [link]
Zhen Xu, Xinjin Li, Yingqi Huan, Veronica Minaya, Renzhe Yu.
The 26th International Conference on Artificial Intelligence in Education (AIED), 2025
Contexts Matter but How? Course-Level Correlates of Performance and Fairness Shift in Predictive Model Transfer. [link]
ā Zhen Xu, ā Joseph Olson, Nicole Pochinki, Jason Zheng, Renzhe Yu.
The 14th Learning Analytics and Knowledge Conference, 713ā724 (LAK), 2024