Zixuan Zhu

I am an MSc student at the School of Physical and Mathematical Sciences, Nanyang Technological University (NTU), graduating in 2026. I received my dual bachelor's degree from Beijing University of Posts and Telecommunications (BUPT) and Queen Mary University of London (QMUL).

I am looking for PhD, RA, or research-internship opportunities, and I am open to research collaborations. Please feel free to reach out, even just for a coffee chat.

My research currently centers on the following topics:

• Self-evolving agents: how agents can continually and stably self-improve from their own experience (UCE).
• Scalable evaluation: how to scale agent evaluation efficiently and in parallel (Harbor), and keep it robust and trustworthy.
• Economics of AI: how to reduce the token cost of agentic reasoning and get more capability from every token, until capable agents become viable on small, widely accessible models.

I am fortunate to collaborate with Prof. Ludwig Schmidt, Lin Shi, Haowei Lin, Xiaoyue Zhou, and Xiang Li on agent benchmarking, and with Senkang Hu on self-evolving agents.