Boyu Gou | The Ohio State University(OSU)

About Me

I am a Ph.D. student at The Ohio State University. I’m working on AI Agents in OSU NLP Group, co-advised by Prof. Yu Su and Prof. Huan Sun. Before joining OSU, I obtained my bachelor’s degree in Computer Science from ShanghaiTech University in Shanghai, China, where I was advised by Prof. Kewei Tu on Structure Prediction in NLP.

Research Interests

I’m broadly interested in Language Agents and Foundation Models.

Currently, I’m primarily working on autonomous GUI agents. If you share any similar interests, or are interested in a research internship, feel free to email me or reach out on LinkedIn to discuss ideas and potential collaborations.

Publications

arXiv

Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents

Vardaan Pahuja, Yadong Lu, Corby Rosset, Boyu Gou, Arindam Mitra, Spencer Whitehead, Yu Su, Ahmed Awadallah

Paper

arXiv

Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents

Yu Gu, Boyuan Zheng, Boyu Gou, Kai Zhang, Cheng Chang, Sanjari Srivastava, Yanan Xie, Peng Qi, Huan Sun, Yu Su

Paper Twitter

NAACL 2025

Tooling or Not Tooling? The Impact of Tools on Language Agents for Chemistry Problem Solving

Botao Yu, Frazier N. Baker, Ziru Chen, Garrett Herb, Boyu Gou, Daniel Adu-Ampratwum, Xia Ning, Huan Sun

Paper Code Homepage Twitter

EMNLP 2024 Demo

WebOlympus: An Open Platform for Web Agents on Live Websites

Boyuan Zheng*, Boyu Gou*, Scott Salisbury*, Zheng Du*, Huan Sun, Yu Su

Paper Code Homepage Twitter

ICLR 2025

Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents

Boyu Gou, Ruohan Wang, Boyuan Zheng, Yanan Xie, Cheng Chang, Yiheng Shu, Huan Sun, Yu Su

Paper Code Homepage Twitter Oral (1.8%)

ICML 2024

GPT-4V(ision) is a Generalist Web Agent,if Grounded

Boyuan Zheng, Boyu Gou, Jihyung Kil, Huan Sun, Yu Su

Paper Code Homepage Twitter

News

[Oct. 2024] Released UGround, a new SOTA GUI visual grounding model that empowers entirely vision-only GUI agents by a new & generic SeeAct-V framework. Have a try with our live demo!
[Jan. 2024] Released SeeAct, a generalist web agent powered by GPT-4V. More sophisticated web agents are on the way! (Accepted at ICML 2024)
[Aug. 2023] Joined OSU, and am honored to work in OSU NLP Group.

Misc

SeeAct: An easy-to-use codebase and Python package designed for autonomous web agents. You can freely test it with any task on any live website with just one click! It is also useful for other agent work as a convenient web browsing implementation.
GUI Agent Paper List: A comprehensive & up-to-date GUI Agent paper list.

Academic Services

Reviewer:
- Main Conference: ICLR 2025
- Workshop: LLMAgents @ ICLR 2024

Education

The Ohio State Univeristy, 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:

SI152 Numerical Optimization, 2022 Fall
- Instructor: Prof. Hao Wang
- Theories, algorithms, and convergence analysis of linear and nonlinear optimization.
CS110&CS110P Computer Architecture I & Computer Architecture I Project, 2022 Spring
- Instructor: Prof. Chundong Wang & Prof. Sören Schwertfeger
- Similar to UC Berkeley CS61C Great Ideas in Computer Architecture. The course homepage is here.
CLPS1001 Intimacy Psychology, 2023 Spring
- Instructor: Dr. Yaqi Cai