|
Junwei Liu Junwei Liu is currently a PhD student in the School of Computer Science, Fudan University. As a member of CodeWisdom Group, he had the invaluable opportunity to work under the guidance and mentorship of Prof. Xin Peng and Prof. Yiling Lou. His research interests mainly focus on Software Engineering and its synergy with Artificial Intelligence, especially large language models(LLMs). Previously, he obtained his B.S. degree in Software Engineering from Fudan in 2022. |
|
[2026.06] 🎉 Our paper, STALL+, on repository-level code completion with static analysis is accepted by TOSEM.
[2026.04] 🎉 Our new work, EvoDev, on end-to-end software development with LLM-based agents is accepted by ISSTA 2026.
[2025.11] 🎉 Our paper "Large Language Model-Based Agents for Software Engineering: A Survey" is accepted by TOSEM.
[2025.09] 🎉 Our paper "Can Agents Fix Agent Issues?" is accepted by NeurIPS 2025.
[2025.05] 🎉 Introducing AgentIssue-Bench - a new benchmark focusing on issues in LLM-based agent systems!
[2024.09] 🎉 Our latest Agent4SE survey has been released. Star our GitHub Repo to keep up with the updates!
Publications |
|
[ISSTA 2026] Towards Iterative End-to-End Software Development: A Feature-Driven Multi-Agent Framework In: proceedings of the 35th International Symposium on Software Testing and Analysis, ISSTA, October 3-9, 2026, Oakland, United States. Junwei Liu, Chen Xu, Chong Wang, Tong Bai, Weitong Chen, Kaseng Wong, Yiling Lou, Xin Peng |
Paper |
|
[TOSEM 2026] STALL+: Boosting LLM-based Repository-level Code Completion with Static Analysis In: ACM Transactions on Software Engineering and Methodology, accepted to appear, 2026 Junwei Liu, Yixuan Chen, Mingwei Liu, Xin Peng, Yiling Lou |
Paper GitHub Repo |
|
[TOSEM 2025] Large Language Model-Based Agents for Software Engineering: A Survey In: ACM Transactions on Software Engineering and Methodology, accepted to appear, 2025 Junwei Liu, Kaixin Wang, Yixuan Chen, Xin Peng, Zhenpeng Chen, Lingming Zhang, Yiling Lou |
Paper GitHub Repo 
|
|
[NeurIPS 2025] Can Agents Fix Agent Issues? In: Proceedings of the 39th Annual Conference on Neural Information Processing Systems, accepted to appear, December 2025, San Diego, USA Alfin Wijaya Rahardja*, Junwei Liu*, Weitong Chen, Zhenpeng Chen, Yiling Lou |
Paper 🏅 Leaderboard GitHub Repo |
|
[ICSE 2024] ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation In: proceedings of the 46th International Conference on Software Engineering, to appear, April 2024, Lisbon, Portugal Xueying Du, Mingwei Liu, Kaixin Wang, Hanlin Wang, Junwei Liu, Yixuan Chen, Jiayi Feng, Chaofeng Sha, Xin Peng, Yiling Lou |
Paper 🏅 Leaderboard Hugging Face [Downloads 30000+] |
|
[ASE 2023] Generating Variable Explanations via Zero-shot Prompt Learning In: proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering, to appear, Sept 2023, Kirchberg, Luxembourg Chong Wang, Yiling Lou, Junwei Liu, Xin Peng |
Paper |
|
[Preprint] Where Does the Performance Go? Understanding and Recovering Performance Regressions in C-to-Rust Translation Zhiqiang Yuan, Chong Wang, Zhenhao Zhou, Junwei Liu, Xin Peng |
Paper |
|
[Preprint] Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution Kai Yu, Zhenhao Zhou, Junhao Zeng, Ying Wang, Xueying Du, Zhiqiang Yuan, Junwei Liu, Ziyu Zhou, Yujia Wang, Chong Wang, Xin Peng |
Paper |
|
[Preprint] Evaluating Instruction-Tuned Large Language Models on Code Comprehension and Generation Zhiqiang Yuan, Junwei Liu, Qiancheng Zi, Mingwei Liu, Xin Peng, Yiling Lou |
Paper |
Academic Services |
- Publicity Chair for LLM4Code'24/26@ICSE
- Program Committee Member for SANER'27
- Track Manager for FSE'27
- Reviewer for TOSEM, TSE, ACL ARR, JoS, EMSE
- External Reviewer for ICSE'24, ASE'24, ISSTA'24-26
Invited Talks |
- [Oct. 2026] Global Technical Service (GTS), Huawei: Towards Verifiable End-to-End Software Development: Feature-Driven Planning and Design Abstraction
- [Oct. 2026] ISSTA 2026: Towards Iterative End-to-End Software Development: A Feature-Driven Multi-Agent Framework
- [Jun. 2026] Agentic AICon 2026: An Agentic Framework for Feature-Driven Development Based on Code Digital Twin
- [Apr. 2026] Consumer Business Group (CBG), Huawei: Code Is Cheap, Show Me the Talk: Deconstructing Harness Engineering from a Software Engineering Perspective
- [Oct. 2024] Quality Intelligence Team, ByteDance: LLM for Software Development and Maintenance (Slides)
- [Sep. 2024] TONGYI Lingma, Aliyun: LLM-based Agents for Software Engineering (Slides)
Honors & Awards |
- National Scholarship, Ministry of Education, China (2026)
- Second-Class Academic Scholarship, Fudan University, China (2023-2025)
- Outstanding Graduate, Fudan University (2022)
- National Endeavor Scholarship, Ministry of Education, China (2018-2021)
Teaching |
- Teaching Assistant, Software Engineering, Undergraduate-level, Fudan University (Spring 2023 & Spring 2025)
|
Last update: Oct. 18, 2026
|