@inproceedings{wang-etal-2026-bridging,
    title = "Bridging Kernel Drivers and Virtual Device Models with {LLM}-Powered Automation",
    author = "Wang, Mingyu  and
      Yu, Bin  and
      Lu, Wenjian  and
      Wang, Zhi  and
      Kefeng, Gao  and
      Wen, Cheng  and
      Lu, Xu  and
      Tian, Cong",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.24/",
    pages = "242--252",
    ISBN = "979-8-89176-392-0",
    abstract = "Linux kernel device drivers are tightly coupled with hardware, making them difficult to execute and test without physical devices. This heavily limits automated code analysis and vulnerability discovery. While manual modeling is unscalable, Large Language Models (LLMs) offer a new approach to scale virtual device construction across the Linux driver ecosystem. In this paper, we present DevGen, an LLM-powered tool that generates QEMU-based virtual devices directly from Linux driver source code. DevGen combines static analysis to gather necessary context, guides the LLM through step-by-step prompting, and uses an automated self-correction loop driven by compilation and execution feedback. To further reduce errors, similar fixes are retrieved from a library of common modeling failures and incorporated into the repair prompt, which supports more targeted corrections in later iterations. The generated devices finally integrate with QEMU and Syzkaller, enabling driver fuzzing without physical hardware. DevGen is evaluated on 50 PCI/PCIe drivers from Linux 6.18 using three mainstream LLMs, and successfully generates usable models for 44 drivers. In these drivers, 24{\%} of them achieve significant improvements in fuzzing coverage, and 7 previously unknown crashes are triggered with 1 CVE assigned. These results demonstrate the practical capability of LLMs to automate complex, system-level code generation tasks."
}