👋 I am James Zhao, a third-year PhD candidate in the School of Computing at the National University of Singapore. I am co-advised by Prof. Bryan Hooi and Prof. See-Kiong Ng. Recently, I am interested in the efficiency of long-horizon agentic tasks and test-time scaling. I always welcome discussions and collaborations, please feel free to reach out! 😃

I am also seeking research internship opportunities. If you have an open position that may be a good fit, I would be happy to connect.

📄 Selected Publications

FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search

FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search

James Xu Zhao, Hui Chen, Bryan Hooi, See-Kiong Ng

Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

James Xu Zhao, Bryan Hooi, See-Kiong Ng

How Does Response Length Affect Long-Form Factuality

How Does Response Length Affect Long-Form Factuality

James Xu Zhao, Jimmy Z.J. Liu, Bryan Hooi, See-Kiong Ng

Automatic Model Selection with Large Language Models for Reasoning

Automatic Model Selection with Large Language Models for Reasoning

James Xu Zhao, Yuxi Xie, Kenji Kawaguchi, Junxian He, Qizhe Xie