# LLM-Driven Kernel Evolution: Automating Driver Updates in Linux

arXiv: https://arxiv.org/abs/2511.18924 · HTML: https://mlsanity.com/paper/2511.18924/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 17 of 17)

- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [SIM-CoT: Supervised Implicit Chain-of-Thought](https://mlsanity.com/paper/2509.20317/) (2025)
- [A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends](https://mlsanity.com/paper/2311.10372/) (2023)
- [Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications](https://mlsanity.com/paper/2503.01245/) (2025)
- [Stable Code Technical Report](https://mlsanity.com/paper/2404.01226/) (2024)
- [KGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution](https://mlsanity.com/paper/2407.02680/) (2024)
- [PatchNet: Hierarchical Deep Learning-Based Stable Patch Identification for the Linux Kernel](https://mlsanity.com/paper/1911.03576/) (2019)
- [An Investigation of Patch Porting Practices of the Linux Kernel Ecosystem](https://mlsanity.com/paper/2402.05212/) (2024)
- [A Large-scale Investigation of Semantically Incompatible APIs behind Compatibility Issues in Android Apps](https://mlsanity.com/paper/2406.17431/) (2024)
- [kAgent: An execution-guided crash resolution agent for the Linux kernel](https://mlsanity.com/paper/2504.20412/) (2025)
- [Code-Survey: An LLM-Driven Methodology for Analyzing Large-Scale Codebases](https://mlsanity.com/paper/2410.01837/) (2024)
- [MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions](https://mlsanity.com/paper/2504.09474/) (2025)
- [Linux Kernel Configurations at Scale: A Dataset for Performance and Evolution Analysis](https://mlsanity.com/paper/2505.07487/) (2025)
- [Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults](https://mlsanity.com/paper/2505.19489/) (2025)
- [An Empirical Study of Configuration Mismatches in Linux](https://mlsanity.com/paper/2110.05828/) (2021)
- [Fast Fixes and Faulty Drivers: An Empirical Analysis of Regression Bug Fixing Times in the Linux Kernel](https://mlsanity.com/paper/2411.02091/) (2024)
- [SoK: Understanding the Attack Surface in Device Driver Isolation Frameworks](https://mlsanity.com/paper/2412.16754/) (2024)

## Built on by (most cited first, 1 of 1)

- [V2X-QA: A Comprehensive Reasoning Dataset and Benchmark for Multimodal Large Language Models in Autonomous Driving Across Ego, Infrastructure, and Cooperative Views](https://mlsanity.com/paper/2604.02710/) (2026)

## 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.