mlsanityData to 7 Oct 2026

LLM-Driven Kernel Evolution: Automating Driver Updates in Linux

arXiv 2511.18924 ↗First posted 24 Nov 2025cs.SE cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Linux kernel evolution breaks drivers through API/ABI changes, semantic shifts, and security-hardening updates. We introduce DRIVEBENCH, an executable corpus of kernelrightarrowdriver 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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 17 of its 45 references that are in the map. First posted on arXiv 24 Nov 2025.

Builds on

17 of 45 references.

References · 17

  1. 2024A Survey on Large Language Models for Code Generationcited by 646
  2. 2023A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trendscited by 66
  3. 2025SIM-CoT: Supervised Implicit Chain-of-Thoughtcited by 63
  4. 2025Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applicationscited by 26
  5. 2024Stable Code Technical Reportcited by 16
  6. 2024KGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolutioncited by 12
  7. 2019PatchNet: Hierarchical Deep Learning-Based Stable Patch Identification for the Linux Kernelcited by 5
  8. 2024An Investigation of Patch Porting Practices of the Linux Kernel Ecosystemcited by 5
  9. 2024A Large-scale Investigation of Semantically Incompatible APIs behind Compatibility Issues in Android Appscited by 5
  10. 2025kAgent: An execution-guided crash resolution agent for the Linux kernelcited by 4
  11. 2024Code-Survey: An LLM-Driven Methodology for Analyzing Large-Scale Codebasescited by 2
  12. 2025MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versionscited by 2
5 more
  1. 2025Linux Kernel Configurations at Scale: A Dataset for Performance and Evolution Analysiscited by 2
  2. 2025Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faultscited by 2
  3. 2021An Empirical Study of Configuration Mismatches in Linuxcited by 1
  4. 2024Fast Fixes and Faulty Drivers: An Empirical Analysis of Regression Bug Fixing Times in the Linux Kernelcited by 1
  5. 2024SoK: Understanding the Attack Surface in Device Driver Isolation Frameworkscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026V2X-QA: A Comprehensive Reasoning Dataset and Benchmark for Multimodal Large Language Models in Autonomous Driving Across Ego, Infrastructure, and Cooperative Viewscited by 6