MaintainCoder: Maintainable Code Generation Under Dynamic Requirements
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908564448083968 |
|---|---|
| author | Wang, Zhengren Ling, Rui Wang, Chufan Yu, Yongan Wang, Sizhe Li, Zhiyu Xiong, Feiyu Zhang, Wentao |
| author_facet | Wang, Zhengren Ling, Rui Wang, Chufan Yu, Yongan Wang, Sizhe Li, Zhiyu Xiong, Feiyu Zhang, Wentao |
| contents | Modern code generation has made significant strides in functional correctness and execution efficiency. However, these systems often overlook a critical dimension in real-world software development: maintainability. To handle dynamic requirements with minimal rework, we propose MaintainCoder as a pioneering solution. It integrates the Waterfall model, design patterns, and multi-agent collaboration to systematically enhance cohesion, reduce coupling, achieving clear responsibility boundaries and better maintainability. We also introduce MaintainCoder, a benchmark comprising requirement changes and novel dynamic metrics on maintenance efforts. Experiments demonstrate that existing code generation methods struggle to meet maintainability standards when requirements evolve. In contrast, MaintainCoder improves dynamic maintainability metrics by more than 60% with even higher correctness of initial codes. Furthermore, while static metrics fail to accurately reflect maintainability and even contradict each other, our proposed dynamic metrics exhibit high consistency. Our work not only provides the foundation for maintainable code generation, but also highlights the need for more realistic and comprehensive code generation research. Resources: https://github.com/IAAR-Shanghai/MaintainCoder. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_24260 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MaintainCoder: Maintainable Code Generation Under Dynamic Requirements Wang, Zhengren Ling, Rui Wang, Chufan Yu, Yongan Wang, Sizhe Li, Zhiyu Xiong, Feiyu Zhang, Wentao Software Engineering Computation and Language Modern code generation has made significant strides in functional correctness and execution efficiency. However, these systems often overlook a critical dimension in real-world software development: maintainability. To handle dynamic requirements with minimal rework, we propose MaintainCoder as a pioneering solution. It integrates the Waterfall model, design patterns, and multi-agent collaboration to systematically enhance cohesion, reduce coupling, achieving clear responsibility boundaries and better maintainability. We also introduce MaintainCoder, a benchmark comprising requirement changes and novel dynamic metrics on maintenance efforts. Experiments demonstrate that existing code generation methods struggle to meet maintainability standards when requirements evolve. In contrast, MaintainCoder improves dynamic maintainability metrics by more than 60% with even higher correctness of initial codes. Furthermore, while static metrics fail to accurately reflect maintainability and even contradict each other, our proposed dynamic metrics exhibit high consistency. Our work not only provides the foundation for maintainable code generation, but also highlights the need for more realistic and comprehensive code generation research. Resources: https://github.com/IAAR-Shanghai/MaintainCoder. |
| title | MaintainCoder: Maintainable Code Generation Under Dynamic Requirements |
| topic | Software Engineering Computation and Language |
| url | https://arxiv.org/abs/2503.24260 |