LLM-Driven Kernel Evolution: Automating Driver Updates in Linux

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kharlamova, Arina, Liu, Jiawen, Zhang, Tianyi, Yang, Xinrui, Alqasimi, Humaid, Sun, Youcheng, Xue, Chun Jason
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911283561889792
author Kharlamova, Arina
Liu, Jiawen
Zhang, Tianyi
Yang, Xinrui
Alqasimi, Humaid
Sun, Youcheng
Xue, Chun Jason
author_facet Kharlamova, Arina
Liu, Jiawen
Zhang, Tianyi
Yang, Xinrui
Alqasimi, Humaid
Sun, Youcheng
Xue, Chun Jason
contents Linux kernel evolution breaks drivers through API/ABI changes, semantic shifts, and security-hardening updates. We introduce DRIVEBENCH, an executable corpus of kernel$\rightarrow$driver co-evolution cases, and AUTODRIVER, a closed-loop, LLM-driven system for automating driver maintenance. The system integrates prompt engineering, multi-agent collaboration, static analysis, and iterative validation to ensure that generated patches are not only syntactically correct but also functionally and semantically consistent with kernel conventions. The corpus spans v5.10-v6.10 with 235 validated cases drawn from 612 candidates. In evaluation across 55 cases, AUTODRIVER achieves 56.4% compilation success; QEMU-based boot verification indicates that compiled patches preserve driver initialization in most instances. By releasing DRIVEBENCH and tooling, we enable reproducible research and a practical route to continuous, safe co-evolution of drivers with the Linux kernel.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18924
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Driven Kernel Evolution: Automating Driver Updates in Linux
Kharlamova, Arina
Liu, Jiawen
Zhang, Tianyi
Yang, Xinrui
Alqasimi, Humaid
Sun, Youcheng
Xue, Chun Jason
Software Engineering
Artificial Intelligence
Linux kernel evolution breaks drivers through API/ABI changes, semantic shifts, and security-hardening updates. We introduce DRIVEBENCH, an executable corpus of kernel$\rightarrow$driver co-evolution cases, and AUTODRIVER, a closed-loop, LLM-driven system for automating driver maintenance. The system integrates prompt engineering, multi-agent collaboration, static analysis, and iterative validation to ensure that generated patches are not only syntactically correct but also functionally and semantically consistent with kernel conventions. The corpus spans v5.10-v6.10 with 235 validated cases drawn from 612 candidates. In evaluation across 55 cases, AUTODRIVER achieves 56.4% compilation success; QEMU-based boot verification indicates that compiled patches preserve driver initialization in most instances. By releasing DRIVEBENCH and tooling, we enable reproducible research and a practical route to continuous, safe co-evolution of drivers with the Linux kernel.
title LLM-Driven Kernel Evolution: Automating Driver Updates in Linux
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2511.18924