Zixuan Wang

About Me

I am Zixuan Wang, a Physics undergraduate at Tsinghua University (class of 2023). My research aims toward human-centered AI and autonomous agentic systems—LLMs that reason, plan, and act with people.

I am a remote research assistant at Carnegie Mellon University (ECE), advised by Prof. Andrea Zanette. During my Fall 2025 exchange at UC San Diego, I was an undergraduate researcher at the UCSD MixLab (HDSI) with Dr. Zhen Wang. Earlier, I was an AI intern at MiroMind AI, mentored by Dr. Yuntao Chen.

Research Interests

My research interests lie in advancing LLM algorithms that enable more reliable, adaptive, and autonomous interaction with humans. I am particularly interested in LLM alignment, leveraging synthetic data, structured supervision, and preference-based training to improve models’ understanding of human intent while ensuring privacy and safety. I also work on agentic LLM systems with long-horizon capabilities, including long-context reasoning, planning, tool use, and self-refinement in real-world grounded environments.

• Agentic LLM Systems🤖: Long-context reasoning, planning, tool use, and self-refinement in real-world grounded environments
• LLM Alignment🔒: Leveraging synthetic data, structured supervision, and preference-based training to improve human intent understanding while ensuring privacy and safety
• Reinforcement Learning for LLMs🧠: Training agents for sustained, multi-turn interactions and long-horizon task completion

Education

• [2023-present] B.S. in Mathematical and Physical Basic Science (Physics), Tsinghua University
  • Minor: Artificial Intelligence
• [Fall 2025] Exchange Student in Computer Science, UC San Diego

Experience

Publications

Technical Reports

Course Projects

Blogs & Notes

Powered by Jekyll and Minimal Light theme.