About Me

I am a Ph.D. student supervised by Prof. Leye Wang at the School of Computer Science, Peking University. Prior to this, I completed my bachelor’s degree in Computer Science at Northwestern Polytechnical University.

My research interests include Academic Data Management, Data Privacy Protection, and related fields. I am passionate about exploring innovative solutions to challenges in Computer Science, Mathematics, and Physics. Recently, I have also been working on AI Agents and Agent Skill Evaluation, especially on practical benchmarking systems for utility and security.

Education

• 2024 - present: Ph.D. student in Computer Science, Peking University
• 2020 - 2024: B.S. in Computer Science, Northwestern Polytechnical University, Kang Jichang Honors Class (康继昌计算机科学拔尖班)

Publications

• SkillTester: Benchmarking Utility and Security of Agent Skills
  Leye Wang, Zixing Wang, Anjie Xu
  arXiv:2603.28815, 2026
  Paper | Code | skilltester.ai

SkillTester is an agent-driven benchmark system for evaluating agent skills from both utility and security perspectives. It compares paired baseline and with-skill executions, preserves raw task-level evidence, and generates structured reports that help users judge whether a skill is useful and safe before adoption.

• ChatPD: An LLM-driven Paper-Dataset Networking System
  Anjie Xu, Ruiqing Ding, Leye Wang
  CCF-A, KDD 2025 Applied Data Science Track
  Paper | Code | Deployed Website | Video

Blog

• 2026-05-02 — From Agent Mania to Research Automation: AI Breaking Through the Frontiers of Knowledge

• 2026-01-20 — After Vibe Code, Vibe Clean: Turning ‘It Runs’ Back Into ‘I Understand’

• 2025-03-29 — OSTEP Memory Virtualization Notes

Awards

• 2024, Outstanding Graduate Student, Northwestern Polytechnical University (西北工业大学优秀毕业生)
• 2023, National Special Prize (University Group), CCF Sinan Cup Quantum Computing Competition (CCF量子计算司南杯全国高校组特等奖)

Experience

• Teaching Assistant of AI Agent Programming Practice by Dr. Bojie Li (Co-Founder & Chief Scientist of Pine AI), Zhongguancun Academy (Course Homepage), 2025 Summer
• Teaching Assistant of Data Structures and Algorithms (A) by Prof. Leye Wang, Peking University, 2024 Fall
• Quantitative Trading Intern, MetaLight Inc., Oct 2023 – Jun 2024
  Built and optimized quantitative trading algorithms for power trading systems

Skills

• Programming Languages: Rust, Python, C++
• I also have some experience with Operating Systems.

Hobbies

Outside of my academic work, I enjoy reading, writing short articles to share my thoughts, and watching anime such as K-On! (轻音少女) and Pretty Derby (赛马娘).