Quanjun Zhang

Quanjun Zhang

Professor at Nanjing University of Science and Technology

I am currently a Professor at the School of Computer Science and Engineering, Nanjing University of Science and Technology. My research focuses on the intersection of artificial intelligence and software engineering, with particular interests in coding agents, automated program repair, software testing, code representation, deep learning system testing and repair, and model security.

Previously, I was a Postdoctoral Research Fellow at Swinburne University of Technology under the supervision of Prof. Yun Yang. I received my Ph.D. from Nanjing University, under the supervision of Prof. Zhenyu Chen and Assoc. Prof. Chunrong Fang.

I am open to collaboration and communication. Please feel free to contact me at quanjunzhang@njust.edu.cn.

đź“š Research Interest

I have published over 50 papers at top international conferences and journals in software engineering, artificial intelligence, and security, including venues such as ICSE, FSE, ASE, ISSTA, ACL, IJCV, TOSEM, TSE, TDSC, SCIS, and EMSE. My research lies at the intersection of artificial intelligence, software engineering, and software security. I am particularly interested in:

  • LLMs and Agents for Software Engineering: coding agents and multi-agent software repair (TOSEM’26), repository-level program repair (TOSEM’26, ASE’26), assertion generation (TSE’25, TOSEM’25, ISSTA’26), unit test generation (ISSTA’25, FSE’25-Tool), and retrieval-augmented software engineering (SCIS’25, JOS’25).
  • Automated Program Repair and Software Maintenance: learning-based program repair (ASE’23, TOSEM’23, ISSTA’22), patch correctness assessment (TSE’24, EMSE’26), vulnerability repair (TDSC’23), actionable warning identification (TOSEM’25, SCIS’24), and code search, summarization, and representation (ICSE’22, TOSEM’23, TSE’24, TOSEM’26).
  • Software Testing and Quality Assurance: assertion and test generation (TSE’25, TOSEM’25, ISSTA’25, ISSTA’26), fuzzing and seed prioritization (TOSEM’24), mobile and crowdsourced testing (TSE’23, TSE’24, FSE’24), and testing of machine translation, GUI, and deep learning systems (TOSEM’24, TOSEM’25, JOS’25).
  • Security of AI and Code Models: backdoor attacks and defenses for neural code models (ACL’23, TOSEM’25, FSE’25), secure code generation and model editing (ISSTA’26), vulnerability repair (TDSC’23), and adversarial testing of AI systems (IJCV’26, TOSEM’25).
Research word cloud generated from publication titles

Selected Publications

Note: * denotes corresponding author; † denotes equal contribution.

  1. TOSEM'26 SGAgent: Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repair. (CCF-A)
    Quanjun Zhang, Chengyu Gao, Yu Han, Ye Shang, Chunrong Fang, Zhenyu Chen, Liang Xiao.
    In ACM Transactions on Software Engineering and Methodology, pages to appear, 2026.

  2. EMSE'26 ComPass: Contrastive Learning for Automated Patch Correctness Assessment in Program Repair. (CCF-B)
    Quanjun Zhang, Ye Shang, Haichuan Hu, Chunrong Fang, Zhenyu Chen, Liang Xiao.
    In Empirical Software Engineering, pages to appear, 2026.

  3. TOSEM'26 A Systematic Literature Review on Large Language Models for Automated Program Repair. (CCF-A)
    Quanjun Zhang, Chunrong Fang, Yuxiang Ma, Yang Xie, Weisong Sun, Yun Yang, Zhenyu Chen.
    In ACM Transactions on Software Engineering and Methodology, pages to appear, 2026.

  4. TSE'25 Improving Retrieval-Augmented Deep Assertion Generation via Joint Training. (CCF-A)
    Quanjun Zhang, Chunrong Fang, Yi Zheng, Ruixiang Qian, Shengcheng Yu, Yuan Zhao, Jianyi Zhou, Yun Yang, Tao Zheng, Zhenyu Chen.
    In IEEE Transactions on Software Engineering, pages to appear, 2025. [Data]

  5. TOSEM'25 Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models. (CCF-A)
    Quanjun Zhang, Chunrong Fang, Yi Zheng, Yaxin Zhang, Yuan Zhao, Rubing Huang, Jianyi Zhou, Yun Yang, Tao Zheng, Zhenyu Chen.
    In ACM Transactions on Software Engineering and Methodology, pages to appear, 2025.

  6. SCIS'25 A Survey on Large Language Models for Software Engineering. (CCF-A)
    Quanjun Zhang, Chunrong Fang, Yang Xie, Yaxin Zhang, Shengcheng Yu, Weisong Sun, Yun Yang, Zhenyu Chen.
    In SCIENCE CHINA Information Sciences, pages to appear, 2025.

  7. FCS'25 TestBench: Evaluating Class-Level Test Case Generation Capability of Large Language Models. (CCF-B)
    Quanjun Zhang, Ye Shang, Chunrong Fang, Siqi Gu, Jianyi Zhou, Zhenyu Chen.
    In Frontiers of Computer Science, pages to appear, 2025.

  8. JOS'25 Research Progress of Retrieval-Augmented Generation in Software Engineering. (CCF-A)
    Quanjun Zhang, Yang Xie, Chunrong Fang*, Shengcheng Yu, Yuan Zhao, Zhenyu Chen.
    In Journal of Software (in Chinese), pages to appear, 2025.

  9. TOSEM'24 Exploring Automated Assertion Generation via Large Language Models. (CCF-A)
    Quanjun Zhang, Weifeng Sun, Chunrong Fang, Bowen Yu, Hongyan Li, Meng Yan, Jianyi Zhou, Zhenyu Chen.
    In ACM Transactions on Software Engineering and Methodology, pages to appear, 2024.

  10. TSE'24 APPT: Boosting Automated Patch Correctness Prediction via Fine-tuning Pre-trained Models. (CCF-A)
    Quanjun Zhang, Chunrong Fang, Weisong Sun, Yan Liu, Tieke He, Xiaodong Hao, Zhenyu Chen.
    In IEEE Transactions on Software Engineering, pages to appear, 2024.

  11. TOSEM'24 Machine Translation Testing via Syntactic Tree Pruning. (CCF-A)
    Quanjun Zhang, Juan Zhai, Chunrong Fang, Jiawei Liu, Weisong Sun, Haichuan Hu, Qingyu Wang.
    In ACM Transactions on Software Engineering and Methodology, 39 pages, 2024. [Data]

  12. TOSEM'23 A Survey of Learning-based Automated Program Repair. (CCF-A)
    Quanjun Zhang, Chunrong Fang, Yuxiang Ma, Weisong Sun, Zhenyu Chen.
    In ACM Transactions on Software Engineering and Methodology, 69 pages, 2023. [PDF] [Data]

  13. TDSC'23 Pre-trained Model-based Automated Software Vulnerability Repair: How Far are We?. (CCF-A)
    Quanjun Zhang, Chunrong Fang, Bowen Yu, Weisong Sun, Tongke Zhang, Zhenyu Chen.
    In IEEE Transactions on Dependable and Secure Computing, pages to appear, 2023. [PDF] [Data]

  14. ASE'23 GAMMA: Revisiting Template-based Automated Program Repair via Mask Prediction. (CCF-A)
    Quanjun Zhang, Chunrong Fang, Tongke Zhang, Bowen Yu, Weisong Sun, Zhenyu Chen.
    In 38th IEEE/ACM International Conference on Automated Software Engineering, pages to appear, 2023.

  15. JSS'22 Test Case Prioritization Using Partial Attention. (CCF-B)
    Quanjun Zhang, Chunrong Fang, Weisong Sun, Shencheng Yu, Yutao Xu, Yulei Liu.
    In Journal of Systems & Software, pages to appear, 2022.

  16. ISSTA'25 A Large-scale Empirical Study on Fine-tuning Large Language Models for Unit Testing. (CCF-A)
    Ye Shang, Quanjun Zhang†, Chunrong Fang, Siqi Gu, Jianyi Zhou, Zhenyu Chen.
    In Proceedings of the ACM SIGSOFT International Symposium on Software Testing and Analysis, pages to appear, 2025.

  17. ISSTA'22 CIRCLE: Continual Repair across Programming Languages. (CCF-A)
    Wei Yuan, Quanjun Zhang†, Tieke He, Chunrong Fang, Nguyen Quoc Viet Hung, Hongzhi Yin.
    In Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis, July 18-22, 2022.