Auto-repair without test cases: How LLMs fix compilation errors in large industrial embedded code
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_ | 1866908595361153024 |
|---|---|
| author | Fu, Han Eldh, Sigrid Wiklund, Kristian Ermedahl, Andreas Haller, Philipp Artho, Cyrille |
| author_facet | Fu, Han Eldh, Sigrid Wiklund, Kristian Ermedahl, Andreas Haller, Philipp Artho, Cyrille |
| contents | The co-development of hardware and software in industrial embedded systems frequently leads to compilation errors during continuous integration (CI). Automated repair of such failures is promising, but existing techniques rely on test cases, which are not available for non-compilable code.
We employ an automated repair approach for compilation errors driven by large language models (LLMs). Our study encompasses the collection of more than 40000 commits from the product's source code. We assess the performance of an industrial CI system enhanced by four state-of-the-art LLMs, comparing their outcomes with manual corrections provided by human programmers. LLM-equipped CI systems can resolve up to 63 % of the compilation errors in our baseline dataset. Among the fixes associated with successful CI builds, 83 % are deemed reasonable. Moreover, LLMs significantly reduce debugging time, with the majority of successful cases completed within 8 minutes, compared to hours typically required for manual debugging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_13575 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Auto-repair without test cases: How LLMs fix compilation errors in large industrial embedded code Fu, Han Eldh, Sigrid Wiklund, Kristian Ermedahl, Andreas Haller, Philipp Artho, Cyrille Software Engineering D.2.5 The co-development of hardware and software in industrial embedded systems frequently leads to compilation errors during continuous integration (CI). Automated repair of such failures is promising, but existing techniques rely on test cases, which are not available for non-compilable code. We employ an automated repair approach for compilation errors driven by large language models (LLMs). Our study encompasses the collection of more than 40000 commits from the product's source code. We assess the performance of an industrial CI system enhanced by four state-of-the-art LLMs, comparing their outcomes with manual corrections provided by human programmers. LLM-equipped CI systems can resolve up to 63 % of the compilation errors in our baseline dataset. Among the fixes associated with successful CI builds, 83 % are deemed reasonable. Moreover, LLMs significantly reduce debugging time, with the majority of successful cases completed within 8 minutes, compared to hours typically required for manual debugging. |
| title | Auto-repair without test cases: How LLMs fix compilation errors in large industrial embedded code |
| topic | Software Engineering D.2.5 |
| url | https://arxiv.org/abs/2510.13575 |