Haichuan Hu

I am a Ph.D. student (2026.1–) in the Department of Computing at The Hong Kong Polytechnic University, supervised by Prof. Wenjie Li. My current research focuses on building language-model systems that understand people better and provide useful, personalized support.

Before starting my Ph.D., I received both my M.Eng. and B.Eng. in Software Engineering from Nanjing University, where I was supervised by Prof. Zhenyu Chen. I also worked on large-scale database systems and LLM applications at Alibaba Cloud, Microsoft, and Alibaba.com.

research interests

Emotional support and personalized alignment
Large language models and LLM agents
AI for software engineering

I am always happy to discuss research ideas and potential collaborations. Please feel free to reach out by email.

selected publications

Learning from Repair Experience: Self-Evolving Agents for Automated Vulnerability Repair

Haichuan Hu, Guoqing Xie, Quanjun Zhang, Jiawei Liu, Shengcheng Yu, Chunrong Fang, Zhenyu Chen, and Liang Xiao

In 49th IEEE/ACM International Conference on Software Engineering, CCF-A, 2027

arXiv BIB GitHub

Download BibTeX

@inproceedings{hu2027repair,
  title = {Learning from Repair Experience: Self-Evolving Agents for Automated Vulnerability Repair},
  author = {Hu, Haichuan and Xie, Guoqing and Zhang, Quanjun and Liu, Jiawei and Yu, Shengcheng and Fang, Chunrong and Chen, Zhenyu and Xiao, Liang},
  booktitle = {49th IEEE/ACM International Conference on Software Engineering},
  year = {2027},
  url = {https://arxiv.org/abs/2605.30105},
}

RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems

Haichuan Hu, Yang Xiao, Mingni Tang, Jiawen Duan, Quanjun Zhang, Congqing He, Hao Zhang, Jiashuo Wang, Johan F. Hoorn, and Wenjie Li

In Findings of the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 15th International Joint Conference on Natural Language Processing, 2026

arXiv BIB GitHub

Download BibTeX

@inproceedings{hu2026rescuebench,
  title = {RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems},
  author = {Hu, Haichuan and Xiao, Yang and Tang, Mingni and Duan, Jiawen and Zhang, Quanjun and He, Congqing and Zhang, Hao and Wang, Jiashuo and Hoorn, Johan F. and Li, Wenjie},
  booktitle = {Findings of the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 15th International Joint Conference on Natural Language Processing},
  year = {2026},
  url = {https://arxiv.org/abs/2609.09657},
}

MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs

Haichuan Hu, Chunrong Fang, Ye Shang, Jiawei Liu, Weifeng Sun, Guoqing Xie, Chenxing Zhong, and Quanjun Zhang

In 41st IEEE/ACM International Conference on Automated Software Engineering, CCF-A, 2026

DOI arXiv BIB GitHub

Download BibTeX

@inproceedings{hu2026multifixer,
  title = {MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs},
  author = {Hu, Haichuan and Fang, Chunrong and Shang, Ye and Liu, Jiawei and Sun, Weifeng and Xie, Guoqing and Zhong, Chenxing and Zhang, Quanjun},
  booktitle = {41st IEEE/ACM International Conference on Automated Software Engineering},
  year = {2026},
  doi = {10.1145/3832783.3837527},
  url = {https://doi.org/10.1145/3832783.3837527},
}

PSearch: Search-based Patch Generation in the Era of LLM-based Automated Program Repair

Haichuan Hu, Ye Shang, Weifeng Sun, and Quanjun Zhang

In 41st IEEE/ACM International Conference on Automated Software Engineering, CCF-A, 2026

DOI arXiv BIB GitHub

Download BibTeX

@inproceedings{hu2026psearch,
  title = {PSearch: Search-based Patch Generation in the Era of LLM-based Automated Program Repair},
  author = {Hu, Haichuan and Shang, Ye and Sun, Weifeng and Zhang, Quanjun},
  booktitle = {41st IEEE/ACM International Conference on Automated Software Engineering},
  year = {2026},
  doi = {10.1145/3832783.3834422},
  url = {https://doi.org/10.1145/3832783.3834422},
}

A Survey of Large Language Models for Legal Tasks: Progress, Prospects and Challenges

Congqing He, Haichuan Hu, Yanli Li, Hao Zhang, and Quanjun Zhang

Computer Science Review, JCR Q1. equal contribution , 2026

DOI BIB GitHub

Download BibTeX

@article{he2026survey,
  title = {A Survey of Large Language Models for Legal Tasks: Progress, Prospects and Challenges},
  author = {He, Congqing and Hu, Haichuan and Li, Yanli and Zhang, Hao and Zhang, Quanjun},
  journal = {Computer Science Review},
  volume = {60},
  pages = {100906},
  year = {2026},
  doi = {10.1016/j.cosrev.2026.100906},
  url = {https://doi.org/10.1016/j.cosrev.2026.100906},
}

Personalized Alignment in the Era of LLMs: A Review of Methodologies, Datasets, Evaluation, and Applications

Haichuan Hu, Xiao Yang, Jiashuo Wang, Quanjun Zhang, Mingni Tang, Changhe Song, Ye Shang, Congqing He, and Wenjie Li

TechRxiv preprint , 2026

DOI BIB GitHub

Download BibTeX

@misc{hu2026personalized,
  title = {Personalized Alignment in the Era of LLMs: A Review of Methodologies, Datasets, Evaluation, and Applications},
  author = {Hu, Haichuan and Yang, Xiao and Wang, Jiashuo and Zhang, Quanjun and Tang, Mingni and Song, Changhe and Shang, Ye and He, Congqing and Li, Wenjie},
  howpublished = {TechRxiv},
  year = {2026},
  doi = {10.36227/techrxiv.177083699.99572896/v1},
  url = {https://doi.org/10.36227/techrxiv.177083699.99572896/v1},
}

reviewing experience

2026 — TSE Reviewer