AutoKFL: Linux Kernel Fault Localization via ReAct-Based Multi-Agent Framework with Dynamic Crash Reproduction
Sensors · 30.06.2026 · 26 (13) · 4129
DOI: 10.3390/s26134129 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 30.06.2026. Verfasst von JungWoo Park und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Gachon University, Seongnam 13120, Republic of Korea. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Fault localization (FL) is the task of identifying code locations responsible for bugs in software, and it is a prerequisite step in the bug-fixing process. FL in large-scale systems such as the Linux kernel involves three core challenges: First, the vast codebase fundamentally complicates fault search. Second, the structural characteristics of the kernel environment severely restrict runtime visibility. Third, the diverse and non-trivial root causes of kernel faults expand the reasoning space exponentially. To address these challenges, we make the following observations: (1) decomposing the analysis process into functionally separated agents progressively narrows the search scope, (2) sufficient information for analysis can be extracted from static artifacts collected at crash time without runtime instrumentation, and (3) iterative interaction among agents extends the search scope to non-trivial root causes. Based on these observations, we propose AutoKFL, an automated FL system for Linux kernel crashes. AutoKFL employs four cooperating large language model (LLM)-based agents—crash observer, code collector, code analyzer, and evidence synthesizer—to perform crash observation, code collection, code analysis, and evidence synthesis in sequence. Each agent operates in a reasoning–acting (ReAct) manner and supports iterative exploration through conditional routing that allows returning to a prior stage when necessary. In experiments on 208 Linux kernel crashes reported on Syzbot, AutoKFL achieved a file-level Recall@1 of 0.77 and a mean reciprocal rank (MRR) of 0.822, outperforming single-LLM-call approaches across both file-level and function-level localization.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Engineering, Gachon University, Seongnam 13120, Republic of Korea.
- Department of Information Security, Gachon University, Seongnam 13120, Republic of Korea.
- Department of Smart Security, Gachon University, Seongnam 13120, Republic of Korea.
ORCID-Profile: JungWoo Park, Minju Kang, Seungho Jeon, Seong Oun Hwang
Zitieren
APA
Park, J., Kang, M., Jeon, S., & Hwang, S. O. (2026). AutoKFL: Linux Kernel Fault Localization via ReAct-Based Multi-Agent Framework with Dynamic Crash Reproduction. Sensors, 26(13), 4129. https://doi.org/10.3390/s26134129
Vancouver
Park J, Kang M, Jeon S, Hwang SO. AutoKFL: Linux Kernel Fault Localization via ReAct-Based Multi-Agent Framework with Dynamic Crash Reproduction. Sensors. 2026;26(13):4129. doi:10.3390/s26134129
BibTeX
@article{Park2026,
author = {Park, JungWoo and Kang, Minju and Jeon, Seungho and Hwang, Seong Oun},
title = {AutoKFL: Linux Kernel Fault Localization via ReAct-Based Multi-Agent Framework with Dynamic Crash Reproduction},
journal = {Sensors},
year = {2026},
volume = {26},
number = {13},
pages = {4129},
doi = {10.3390/s26134129}
}
EUVIMED