Biography

I am an undergraduate student in the IEEE Honor Class at Shanghai Jiao Tong University, majoring in Computer Science and Technology. I am fortunately advised by Prof. Weinan Zhang in the Apex Data & Knowledge Management Lab.

Previously, I was a summer visiting student at the Xtra Computing Group, National University of Singapore, advised by Prof. Bingsheng He.

My research interests include Knowledge Tracing, LLM Agents, and Software Engineering Capabilities for LLMs. Feel free to reach out via email!

Education

Shanghai Jiao Tong University Sept. 2022 – Present
B.Eng. in Computer Science and Technology (IEEE Honor Class)
Core Academic Credits: 92.88  |  GPA: 4.06 / 4.3  |  Rank: 8 / 94

Publications

CoreCodeBench: A Configurable Multi-Scenario Repository-Level Benchmark
Lingyue Fu, Hao Guan, Bolun Zhang, Haowei Yuan, Yaoming Zhu, Jun Xu, Zongyu Wang, Lin Qiu, Xunliang Cai, Xuezhi Cao, Weiwen Liu, Weinan Zhang, Yong Yu
Preprint, 2025
  • Introduces CorePipe and CoreCodeBench, a comprehensive framework designed to evaluate LLMs within realistic, multi-scenario software engineering contexts.
  • Addresses existing benchmark limitations by simulating complex workflows to provide deeper insights into model performance on real-world coding tasks.
arXiv Paper
SINKT: A Structure-Aware Inductive Knowledge Tracing Model with Large Language Model
Lingyue Fu, Hao Guan, Kounianhua Du, Jianghao Lin, Wei Xia, Ruiming Tang, Yasheng Wang, Weinan Zhang, Yong Yu
CIKM 2024
  • Proposed a novel Structure-Aware Inductive Knowledge Tracing Model with Large Language Model (SINKT).
  • Utilized LLMs for the first time to carefully inject open-world knowledge into knowledge tracing.
arXiv Paper
Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation
Lingyue Fu, Bolun Zhang, Hao Guan, Yaoming Zhu, Lin Qiu, Weiwen Liu, Xuezhi Cao, Xunliang Cai, Weinan Zhang, Yong Yu
Preprint, 2025
  • Proposed an agent-driven benchmark construction pipeline with human supervision, introducing PRDBench with 50 real-world Python projects spanning 20 domains.
  • Presented PRDJudge, a fine-tuned evaluation model achieving over 90% human alignment, providing a scalable and accurate framework for assessing code agents.
arXiv Paper

Experience

Apex Data & Knowledge Management Lab, SJTU Sept. 2023 – Present
Research Assistant · Advised by Prof. Weinan Zhang
  • Knowledge Tracing
  • LLM Agent
Xtra Computing Group, National University of Singapore June 2024 – Sept. 2024
Summer Visiting Student · Advised by Prof. Bingsheng He
  • Graph-System Research
National Undergraduate Innovative Test Program, SJTU May 2023 – Oct. 2023
Researcher · Advised by Yutong Liu
  • Situation Awareness

Honors & Awards

  • China National Scholarship 2023 – 2024
  • Outstanding Scholarship of the 88th Grade Alumni Fund 2024 – 2025
  • Zhiyuan Honor Scholarship 2023 – 2025
  • SMC Takata Scholarship 2022 – 2023

Technical Skills

  • Programming: Python, C/C++, JavaScript, HTML/CSS, Flask, Verilog, Cypher
  • Developer Tools: Git, Docker, Neo4j, VS Code, CLion