Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces
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_ | 1866912982439559168 |
|---|---|
| author | Silva, André Thorén, Gustav Monperrus, Martin |
| author_facet | Silva, André Thorén, Gustav Monperrus, Martin |
| contents | Automatic program repair seeks to generate correct code from buggy programs, with most approaches searching the correct program in a discrete, symbolic space of source code tokens. This symbolic search is fundamentally limited by its inability to directly reason about program behavior. We introduce Gradient-Based Program Repair (GBPR), a new approach that recasts program repair as continuous optimization in a differentiable numerical program space. Our core insight is to compile symbolic programs into differentiable numerical representations, enabling search in the numerical program space directly guided by program behavior. To evaluate GBPR, we present RaspBugs, a new benchmark of 1,466 buggy symbolic RASP programs and their respective numerical representations. Our experiments demonstrate that GBPR can effectively repair buggy symbolic programs by gradient-based optimization in the numerical program space, with convincing repair trajectories. To our knowledge, we are the first to state program repair as continuous optimization in a numerical program space. Our work demonstrates the feasibility of this direction for program repair research, bridging continuous optimization and program behavior. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_17703 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces Silva, André Thorén, Gustav Monperrus, Martin Programming Languages Machine Learning Software Engineering Automatic program repair seeks to generate correct code from buggy programs, with most approaches searching the correct program in a discrete, symbolic space of source code tokens. This symbolic search is fundamentally limited by its inability to directly reason about program behavior. We introduce Gradient-Based Program Repair (GBPR), a new approach that recasts program repair as continuous optimization in a differentiable numerical program space. Our core insight is to compile symbolic programs into differentiable numerical representations, enabling search in the numerical program space directly guided by program behavior. To evaluate GBPR, we present RaspBugs, a new benchmark of 1,466 buggy symbolic RASP programs and their respective numerical representations. Our experiments demonstrate that GBPR can effectively repair buggy symbolic programs by gradient-based optimization in the numerical program space, with convincing repair trajectories. To our knowledge, we are the first to state program repair as continuous optimization in a numerical program space. Our work demonstrates the feasibility of this direction for program repair research, bridging continuous optimization and program behavior. |
| title | Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces |
| topic | Programming Languages Machine Learning Software Engineering |
| url | https://arxiv.org/abs/2505.17703 |