Skip to content

Paper

Paper Preview

Download Full PDF

Paper Information

Title: Advances and Frontiers of LLM-based Issue Resolution in Software Engineering A Comprehensive Survey

Authors: Caihua Li, Lianghong Guo, Yanlin Wang, Wei Tao, Zhenyu Shan, Mingwei Liu, Jiachi Chen, Haoyu Song, Duyu Tang, Hongyu Zhang, Zibin Zheng

Institutions: Sun Yat-sen University, Independent Researcher, Hangzhou Normal University, Zhejiang University, Huawei Technologies Co, Ltd, Chongqing University

Abstract: Issue resolution, a complex Software Engineering (SWE) task integral to real-world development, has emerged as a compelling challenge for artificial intelligence. The establishment of benchmarks like SWE-bench revealed this task as profoundly difficult for large language models, thereby significantly accelerating the evolution of autonomous coding agents. This paper presents a systematic survey of this emerging domain. We begin by examining data construction pipelines, covering automated collection and synthesis approaches. We then provide a comprehensive analysis of methodologies, spanning training-free frameworks with their modular components to training-based techniques, including supervised fine-tuning and reinforcement learning. Subsequently, we discuss critical analyses of data quality and agent behavior, alongside practical applications. Finally, we identify key challenges and outline promising directions for future research. An open-source repository is maintained at https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution to serve as a dynamic resource in this field.

Citation

If you use this project or related survey in your research or system, please cite the following BibTeX:

@misc{li2025awesome_issue_resolution,
    title       = {Advances and Frontiers of LLM-based Issue Resolution in Software Engineering A Comprehensive Survey},
    author      = {Caihua Li and Lianghong Guo and Yanlin Wang and Daya Guo and Wei Tao and Zhenyu Shan and Mingwei Liu and Jiachi Chen and Haoyu Song and Duyu Tang and Hongyu Zhang and Zibin Zheng},
    year        = {2025},
    howpublished = {\url{https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution}}
}

Once published on arXiv or at a conference, please replace the entry with the official citation information (authors, DOI/arXiv ID, conference name, etc.).