Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2603.27130 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917381797838848 |
|---|---|
| author | Mao, Tianhao Zhao, Dongfang Tang, Haixu Wang, Xiaofeng Zhang, Hang |
| author_facet | Mao, Tianhao Zhao, Dongfang Tang, Haixu Wang, Xiaofeng Zhang, Hang |
| contents | Large language models (LLMs) are increasingly used in software development, generating code that ranges from short snippets to substantial project components. As AI-generated code becomes more common in real-world repositories, it is important to understand how it differs from human-written code and how AI assistance may influence development practices. However, existing studies have largely relied on small-scale or controlled settings, leaving a limited understanding of AI-generated code in the wild.
In this work, we present a large-scale empirical study of AI-generated code collected from real-world repositories. We examine both code-level properties, including complexity, structural characteristics, and defect-related indicators, and commit-level characteristics, such as commit size, activity patterns, and post-commit evolution. To support this study, we develop a detection pipeline that combines heuristic filtering with LLM-based classification to identify AI-generated code and construct a large-scale dataset for analysis.
Our study provides a comprehensive view of the characteristics of AI-generated code in practice and highlights how AI-assisted development differs from conventional human-driven development. These findings contribute to a better understanding of the real-world impact of AI-assisted programming and offer an empirical basis for future research on AI-generated software. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27130 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Large-Scale Empirical Study of AI-Generated Code in Real-World Repositories Mao, Tianhao Zhao, Dongfang Tang, Haixu Wang, Xiaofeng Zhang, Hang Software Engineering Large language models (LLMs) are increasingly used in software development, generating code that ranges from short snippets to substantial project components. As AI-generated code becomes more common in real-world repositories, it is important to understand how it differs from human-written code and how AI assistance may influence development practices. However, existing studies have largely relied on small-scale or controlled settings, leaving a limited understanding of AI-generated code in the wild. In this work, we present a large-scale empirical study of AI-generated code collected from real-world repositories. We examine both code-level properties, including complexity, structural characteristics, and defect-related indicators, and commit-level characteristics, such as commit size, activity patterns, and post-commit evolution. To support this study, we develop a detection pipeline that combines heuristic filtering with LLM-based classification to identify AI-generated code and construct a large-scale dataset for analysis. Our study provides a comprehensive view of the characteristics of AI-generated code in practice and highlights how AI-assisted development differs from conventional human-driven development. These findings contribute to a better understanding of the real-world impact of AI-assisted programming and offer an empirical basis for future research on AI-generated software. |
| title | A Large-Scale Empirical Study of AI-Generated Code in Real-World Repositories |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2603.27130 |