CrashFixer: A crash resolution agent for the Linux kernel
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_ | 1866910941835165696 |
|---|---|
| author | Mathai, Alex Huang, Chenxi Ma, Suwei Kim, Jihwan Mitchell, Hailie Nogikh, Aleksandr Maniatis, Petros Ivančić, Franjo Yang, Junfeng Ray, Baishakhi |
| author_facet | Mathai, Alex Huang, Chenxi Ma, Suwei Kim, Jihwan Mitchell, Hailie Nogikh, Aleksandr Maniatis, Petros Ivančić, Franjo Yang, Junfeng Ray, Baishakhi |
| contents | Code large language models (LLMs) have shown impressive capabilities on a multitude of software engineering tasks. In particular, they have demonstrated remarkable utility in the task of code repair. However, common benchmarks used to evaluate the performance of code LLMs are often limited to small-scale settings. In this work, we build upon kGym, which shares a benchmark for system-level Linux kernel bugs and a platform to run experiments on the Linux kernel.
This paper introduces CrashFixer, the first LLM-based software repair agent that is applicable to Linux kernel bugs. Inspired by the typical workflow of a kernel developer, we identify the key capabilities an expert developer leverages to resolve a kernel crash. Using this as our guide, we revisit the kGym platform and identify key system improvements needed to practically run LLM-based agents at the scale of the Linux kernel (50K files and 20M lines of code). We implement these changes by extending kGym to create an improved platform - called kGymSuite, which will be open-sourced. Finally, the paper presents an evaluation of various repair strategies for such complex kernel bugs and showcases the value of explicitly generating a hypothesis before attempting to fix bugs in complex systems such as the Linux kernel. We also evaluated CrashFixer's capabilities on still open bugs, and found at least two patch suggestions considered plausible to resolve the reported bug. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20412 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CrashFixer: A crash resolution agent for the Linux kernel Mathai, Alex Huang, Chenxi Ma, Suwei Kim, Jihwan Mitchell, Hailie Nogikh, Aleksandr Maniatis, Petros Ivančić, Franjo Yang, Junfeng Ray, Baishakhi Software Engineering Artificial Intelligence Operating Systems Code large language models (LLMs) have shown impressive capabilities on a multitude of software engineering tasks. In particular, they have demonstrated remarkable utility in the task of code repair. However, common benchmarks used to evaluate the performance of code LLMs are often limited to small-scale settings. In this work, we build upon kGym, which shares a benchmark for system-level Linux kernel bugs and a platform to run experiments on the Linux kernel. This paper introduces CrashFixer, the first LLM-based software repair agent that is applicable to Linux kernel bugs. Inspired by the typical workflow of a kernel developer, we identify the key capabilities an expert developer leverages to resolve a kernel crash. Using this as our guide, we revisit the kGym platform and identify key system improvements needed to practically run LLM-based agents at the scale of the Linux kernel (50K files and 20M lines of code). We implement these changes by extending kGym to create an improved platform - called kGymSuite, which will be open-sourced. Finally, the paper presents an evaluation of various repair strategies for such complex kernel bugs and showcases the value of explicitly generating a hypothesis before attempting to fix bugs in complex systems such as the Linux kernel. We also evaluated CrashFixer's capabilities on still open bugs, and found at least two patch suggestions considered plausible to resolve the reported bug. |
| title | CrashFixer: A crash resolution agent for the Linux kernel |
| topic | Software Engineering Artificial Intelligence Operating Systems |
| url | https://arxiv.org/abs/2504.20412 |