paper-with-me

Papers

LLM-Driven Kernel Evolution: Automating Driver Updates in Linux

2025-11-24 · Arina Kharlamova, Jiawen Liu, Tianyi Zhang, Xinrui Yang, Humaid Alqasimi, Youcheng Sun, Chun Jason Xue arxiv

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.

📄 PDF Abstract BibTeX arXiv:2511.18924

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineering

Similar Papers 제목 키워드 기반

Boardwalk Empire: How Generative AI is Revolutionizing Economic Paradigms

2024-10-19 · Subramanyam Sahoo, Kamlesh Dutta

The relentless pursuit of technological advancements has ushered in a new era where artificial intelligence (AI) is not only a powerful tool but also a critical economic driver. At the forefront of this transformation is…

AKG kernel Agent: A Multi-Agent Framework for Cross-Platform Kernel Synthesis

2025-12-29 · Jinye Du, Quan Yuan, Zuyao Zhang, Yanzhi Yi 외 arxiv

Modern AI models demand high-performance computation kernels. The growing complexity of LLMs, multimodal architectures, and recommendation systems, combined with techniques like sparsity and quantization, creates signifi…

Recommendation SystemsCode Generation

EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling

2026-06-25 · Qingcan Kang, Mingyang Liu, Xiaojin Fu, Shixiong Kai 외 arxiv

Automating optimization modeling from natural language with large language models (LLMs) faces two key challenges. First, training corpora lack structural diversity. Second, data generation pipelines remain static and de…

Reinforcement Learning

Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts

2026-05-08 · Zixuan Huang, Da Chen, Kecheng Huang, Lihao Yin 외 arxiv

Generating high-performance GPU kernels remains challenging due to the need for both correctness and hardware-aware optimization. While large language models (LLMs) show promise in code generation, they often fail to pro…

Code Generation

Model Evolution Under Zeroth-Order Optimization: A Neural Tangent Kernel Perspective

2026-03-22 · Chen Zhang, Yuxin Cheng, Chenchen Ding, Shuqi Wang 외 arxiv

Zeroth-order (ZO) optimization enables memory-efficient training of neural networks by estimating gradients via forward passes only, eliminating the need for backpropagation. However, the stochastic nature of gradient es…