Computer-Use Agents
Multimodal agents that perceive graphical interfaces, plan across applications, and execute long-horizon computer tasks.
Agent SPhD Student in Computer Science
Shuyu Gan 甘书宇
Pronounced: SHOO-yoo GAHN
University of Minnesota, Twin Cities
I am a Computer Science PhD student at the University of Minnesota, where I work with Minnesota NLP and the Optimization for AI Lab. I am co-advised by Prof. Dongyeop Kang and Prof. Mingyi Hong.
My research interests include agentic AI, LLM alignment, inference-time reasoning, and computer-use agents. My long-term goal is to develop general-purpose agents that can reliably complete complex computer tasks.
I received my bachelor's degree in Computer Science and Technology from the Turing Class at Zhejiang University in 2024.
Current Research
01 / 03
Computer-use agents
Multimodal agents for graphical interfaces and long-horizon tasks.
Research Interests
Inference-Time Reasoning
Methods for improving agent and language-model reasoning at inference time, including settings with difficult-to-verify feedback.
Scaling Unverifiable RewardsAlignment and Personalization
Evaluation and modeling of latent user preferences for more adaptive and controllable language-model interactions.
Latent PreferencesNews
Do LLMs Recognize Your Latent Preferences? was accepted to COLM 2026.
Scaling Unverifiable Rewards was accepted to ACL 2026 Findings.
A2P-Vis received an Honorable Mention at the VISxGenAI Workshop at IEEE VIS 2025.
Agent S was accepted to ICLR 2025.
I graduated from Zhejiang University and was nominated as an Outstanding Graduate of Zhejiang University.
Research Experience
Jun 2026 - Present
Research Intern
Applied Sciences Group, Microsoft
Mentored by Yinheng Li, studying whether AI agents can autonomously supervise model training.
Jun 2025 - Present
Graduate Research Assistant
Minnesota NLP and OptimAI Lab, University of Minnesota
Agentic AI and inference-time reasoning, advised by Prof. Dongyeop Kang and Prof. Mingyi Hong.
Jun 2024 - Nov 2024
Undergraduate Visiting Research Intern
ERIC Lab, UC Santa Cruz
Worked with Prof. Xin Eric Wang on Agent S, an MLLM-based framework for computer-use agents.
Jul 2023 - Sep 2023
Undergraduate Visiting Research Intern
mlPC Lab, UC San Diego
Studied concept-guided diffusion training with Prof. Zhuowen Tu.
Feb 2023 - May 2023
Research Intern
IDEA Lab, Zhejiang University
Worked on culture-aware multimodal co-speech gesture generation with Prof. Lingyun Sun.
Selected Publications
Google ScholarACL Findings 2026
Scaling Unverifiable Rewards: A Case Study on Visual Insights
Shuyu Gan, J. Mooney, P. Hao, R. Wang, M. Hong, Q. Wang, D. Kang
PaperCOLM 2026
Do LLMs Recognize Your Latent Preferences? A Benchmark for Latent Information Discovery in Personalized Interaction
I. Tsaknakis, B. Song, Shuyu Gan, D. Kang, A. Garcia, G. Liu, C. Fleming, M. Hong
PaperVISxGenAI 2025
A2P-Vis: An Analyzer-to-Presenter Agentic Pipeline for Visual Insights Generation and Reporting
Shuyu Gan, R. Wang, J. Mooney, D. Kang
Honorable Mention
PaperICLR 2025
Agent S: An Open Agentic Framework that Uses Computers Like a Human
S. Agashe, J. Han, Shuyu Gan, J. Yang, A. Li, X. E. Wang
PaperACM MM 2023
Cultural Self-Adaptive Multimodal Gesture Generation Based on Multiple Culture Gesture Dataset
J. Wu, S. Chen, Shuyu Gan, W. Li, C. Yang, L. Sun
PaperPersonal
Outside research, I enjoy playing CS2 and Valorant, distance running, and badminton. I was a member of Zhejiang University's Kuafu Long Distance Alliance for three years and have participated in the 1500m race and half marathon.
For research discussions or collaboration, please contact me at gan00067@umn.edu.