About

Hi, I'm Boyu — a Ph.D. student at The Ohio State University, fortunate to be co-advised by Prof. Yu Su and Prof. Huan Sun at the OSU NLP Group. I also intern at NeoCognition, where we work on self-improving, specialized agents.

My research focuses on building capable and reliable GUI agents — language agents that act like humans in the digital world.

At OSU NLP, we built SeeAct, one of the first fully open-source multimodal web agents. We argued for vision-only, human-like agents and identified GUI visual grounding as the major bottleneck at the time (UGround). We also studied the evaluation of such agents on both short-to-medium-horizon (Multimodal-Mind2Web, Online-Mind2Web) and long-horizon (Mind2Web 2) tasks, with novel LLM- and Agent-as-a-Judge evaluation paradigms.

I'm currently focused on planning, reasoning, and self-improvement for GUI agents. If any of this resonates, I'd love to hear from you — drop me an email to discuss or explore collaboration.

News

  • 2025.06
    Mind2Web 2 released — a benchmark for agentic search systems (web agents, Deep Research) on realistic, long-horizon, time-varying tasks. NeurIPS 2025
  • 2025.02
    UGround accepted to ICLR 2025 Oral
  • 2024.08
    Released UGround — entirely vision-only GUI agents under the SeeAct-V framework with a new SOTA GUI grounding model.
  • 2024.01
    Released SeeAct, a generalist web agent powered by GPT-4V. ICML 2024
  • 2023.08
    Joined OSU and the OSU NLP Group.

Selected Publications

NeurIPS'25 D&B
Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
Boyu Gou*, Zanming Huang*, Yuting Ning*, Yu Gu, Michael Lin, Weijian Qi, Andrei Kopanev, Botao Yu, Bernal Jiménez Gutiérrez, Yiheng Shu, Chan Hee Song, Jiaman Wu, Shijie Chen, Hanane Nour Moussa, Tianshu Zhang, Jian Xie, Yifei Li, Tianci Xue, Zeyi Liao, Kai Zhang, Boyuan Zheng, Zhaowei Cai, Viktor Rozgic, Morteza Ziyadi, Huan Sun, Yu Su (w/ Amazon AGI)
PDF Code Project

Projects

SeeAct ↗ —
A codebase and Python package for autonomous web agents. Test any task on any live website with one click.
GUI Agent Paper List ↗ —
A comprehensive and up-to-date GUI Agent paper list.
Lorvex ↗
A personal vibe coding project — an AI-native todo and scheduling app. Highly recommended to try.

Academic Services

Education

  • The Ohio State University · US
    Ph.D. in Computer Science and Engineering
    2023.08 — Present
  • ShanghaiTech University · China
    B.Eng. in Computer Science and Technology
    2019.08 — 2023.06

Teaching

Teaching Assistant at ShanghaiTech University.