Learning-Based Automated Program Repair: A Systematic Literature Review
Software often contains defects, and automated repair techniques offer a promising way to address these issues. This paper examines the current state of research in learning-based automated program repair (APR). It reviews existing learning-based APR approaches and systematically categorizes them into five major types: supervised learning, unsupervised learning, transfer learning, ensemble learning, and language model learning. Finally, the paper discusses the challenges faced in this field, providing valuable insights for future research.
Authors
- Dongcheng Li (ORCID: https://orcid.org/0000-0001-9598-0651)
- W. Eric Wong (ORCID: https://orcid.org/0000-0002-1021-4753)
- Man Zhao (ORCID: https://orcid.org/0000-0001-8882-2954)
- Qing Chen (ORCID: https://orcid.org/0000-0002-7919-5159)
- Hui Li (ORCID: https://orcid.org/0000-0002-8866-5941)
Institutions
- The University of Texas at Dallas (US)
- Cal Poly Humboldt (US)
- China University of Geosciences (CN)
- California State Polytechnic University (US)
Publication Details
- Journal
- Complex System Modeling and Simulation
- Published
- 2025-04-17
- DOI
- https://doi.org/10.23919/csms.2025.0004
- Primary Topic
- Software Testing and Debugging Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00