Towards Better Linux Kernel Fault Localization: Leveraging Contrastive Reasoning and Hierarchical Context Analysis
2026-07-01 • Software Engineering
Software Engineering
AI summaryⓘ
The authors present CoHiKer, a new method to help find bugs in the Linux kernel, which is very complex and hard to debug. CoHiKer uses a special approach called contrastive reasoning to compare differences between test cases that pass and fail, helping pinpoint the bug's root cause. It also analyzes the kernel code step-by-step, from files down to specific methods, using kernel-specific knowledge rather than treating the code as plain text. Their tests show CoHiKer finds bugs more accurately and efficiently than existing tools and also works well on other software datasets.
Linux kernelfault localizationlarge language modelscontrastive reasoninghierarchical context analysisbug reportssystem callscode mutationsoftware debuggingtoken consumption
Authors
Haichi Wang, Ruiguo Yu, Yesong Pang, Yingquan Zhao, Junjie Chen, Jiajun Jiang, Zan Wang
Abstract
Debugging the Linux kernel remains a formidable challenge due to its vast codebase, complex architecture, and low-level programming intricacies. Effective fault localization (FL) is thus essential for efficient kernel debugging and maintenance. While existing FL techniques (both traditional and LLM-based) have shown promise in general-purpose software, they are ill-suited for the kernel context. In particular, recent LLM-based techniques often treat bug reports and source code as plain text, lacking deep integration of kernel-specific knowledge, which limits their ability to identify root causes and achieve fine-grained localization. We present CoHiKer, a novel LLM-based FL technique tailored to the Linux kernel. CoHiKer introduces two key innovations: (1) contrastive reasoning, which identifies root causes by analyzing the behavioral divergence between carefully mutated passing and failing test cases, and (2) hierarchical context analysis, which systematically narrows the localization scope from files to methods by integrating crash reports, syscall semantics, inter-file dependencies, and kernel-specific features. Unlike prior techniques that rely on static understanding and full-code input, CoHiKer decomposes the localization task and enables structured LLM prompting to reason semantically over meaningful contexts. We evaluate CoHiKer on an extended Linux kernel bug dataset against five state-of-the-art baselines. CoHiKer consistently outperforms all competitors, improving Top-1 localization accuracy by up to 26.07% at the file level and 56.85% at the method level over state-of-the-art LLM-based baselines, while achieving up to 8.84% and 28.9% reductions in token consumption, respectively. Furthermore, CoHiKer demonstrates strong generalizability on the non-kernel dataset, with comparable gains (15.5% and 5.3% in Top-1 at file and method levels).