{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T01:46:17Z","timestamp":1782870377008,"version":"3.54.5"},"reference-count":35,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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\u2014crash observer, code collector, code analyzer, and evidence synthesizer\u2014to perform crash observation, code collection, code analysis, and evidence synthesis in sequence. Each agent operates in a reasoning\u2013acting (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.<\/jats:p>","DOI":"10.3390\/s26134129","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:50:37Z","timestamp":1782867037000},"page":"4129","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AutoKFL: Linux Kernel Fault Localization via ReAct-Based Multi-Agent Framework with Dynamic Crash Reproduction"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3137-4955","authenticated-orcid":false,"given":"JungWoo","family":"Park","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Gachon University, Seongnam 13120, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4030-6965","authenticated-orcid":false,"given":"Minju","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Information Security, Gachon University, Seongnam 13120, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7116-6062","authenticated-orcid":false,"given":"Seungho","family":"Jeon","sequence":"additional","affiliation":[{"name":"Department of Smart Security, Gachon University, Seongnam 13120, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4240-6255","authenticated-orcid":false,"given":"Seong Oun","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Gachon University, Seongnam 13120, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"B\u00f6hme, M., Soremekun, E., Chattopadhyay, S., Ugherughe, E., and Zeller, A. (2017, January 4\u20138). Where Is the Bug and How Is It Fixed? An Experiment with Practitioners. Proceedings of the 11th Joint Meeting on Foundations of Software Engineering (ESEC\/FSE 2017), Paderborn, Germany.","DOI":"10.1145\/3106237.3106255"},{"key":"ref_2","unstructured":"Zhou, Z., Huang, Z., He, Y., Wang, C., Wang, J., Wu, Y., Peng, X., and Lou, Y. (2025). Benchmarking and Enhancing LLM Agents in Localizing Linux Kernel Bugs. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Abreu, R., Zoeteweij, P., and van Gemund, A.J.C. (2006, January 18\u201320). An Evaluation of Similarity Coefficients for Software Fault Localization. Proceedings of the 12th Pacific Rim International Symposium on Dependable Computing (PRDC 2006), Riverside, CA, USA.","DOI":"10.1109\/PRDC.2006.18"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1109\/TR.2013.2285319","article-title":"The DStar Method for Effective Software Fault Localization","volume":"63","author":"Wong","year":"2014","journal-title":"IEEE Trans. Reliab."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zhou, J., Zhang, H., and Lo, D. (2012, January 2\u20139). Where Should the Bugs Be Fixed? More Accurate Information Retrieval-Based Bug Localization Based on Bug Reports. Proceedings of the 34th International Conference on Software Engineering (ICSE 2012), Zurich, Switzerland.","DOI":"10.1109\/ICSE.2012.6227210"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Saha, R.K., Lease, M., Khurshid, S., and Perry, D.E. (2013, January 11\u201315). Improving Bug Localization Using Structured Information Retrieval. Proceedings of the 28th IEEE\/ACM International Conference on Automated Software Engineering (ASE 2013), Silicon Valley, CA, USA.","DOI":"10.1109\/ASE.2013.6693093"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Li, X., Li, W., Zhang, Y., and Zhang, L. (2019, January 15\u201319). DeepFL: Integrating Multiple Fault Diagnosis Dimensions for Deep Fault Localization. Proceedings of the 28th ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2019), Beijing, China.","DOI":"10.1145\/3293882.3330574"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Sohn, J., and Yoo, S. (2017, January 10\u201314). FLUCCS: Using Code and Change Metrics to Improve Fault Localization. Proceedings of the 26th ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2017), Santa Barbara, CA, USA.","DOI":"10.1145\/3092703.3092717"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1145\/3660771","article-title":"A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization","volume":"1","author":"Kang","year":"2024","journal-title":"Proc. ACM Softw. Eng."},{"key":"ref_10","unstructured":"Qin, Y., Wang, S., Lou, Y., Dong, J., Wang, K., Li, X., and Mao, X. (2025). AgentFL: Scaling LLM-Based Fault Localization to Project-Level Context. arXiv."},{"key":"ref_11","unstructured":"Torvalds, L. (2026, May 01). The Linux Kernel, Tag: V7.0. Available online: https:\/\/github.com\/torvalds\/linux."},{"key":"ref_12","unstructured":"Vyukov, D. (2026, May 01). syzkaller: An Unsupervised Coverage-Guided Kernel Fuzzer. Available online: https:\/\/github.com\/google\/syzkaller."},{"key":"ref_13","unstructured":"Bellard, F. (2005, January 10\u201315). QEMU, a Fast and Portable Dynamic Translator. Proceedings of the USENIX Annual Technical Conference (USENIX ATC 2005), Anaheim, CA, USA."},{"key":"ref_14","unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2023, January 1\u20135). ReAct: Synergizing Reasoning and Acting in Language Models. Proceedings of the 11th International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Xie, H., Lei, Y., Yan, M., Yu, Y., Xia, X., and Mao, X. (2022, January 21\u201329). A Universal Data Augmentation Approach for Fault Localization. Proceedings of the 44th International Conference on Software Engineering (ICSE 2022), Pittsburgh, PA, USA.","DOI":"10.1145\/3510003.3510136"},{"key":"ref_16","unstructured":"Sohn, K., Lee, H., and Yan, X. (2015, January 7\u201312). Learning Structured Output Representation Using Deep Conditional Generative Models. Proceedings of the Advances in Neural Information Processing Systems 28 (NeurIPS 2015), Montreal, QC, Canada."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Callaghan, D., and Fischer, B. (2023, January 17\u201321). Improving Spectrum-Based Localization of Multiple Faults by Iterative Test Suite Reduction. Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2023), Seattle, WA, USA.","DOI":"10.1145\/3597926.3598148"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1007\/s10664-025-10761-8","article-title":"SBEST: Spectrum-Based Fault Localization Without Fault-Triggering Tests","volume":"31","author":"Rafi","year":"2026","journal-title":"Empir. Softw. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Murali, V., Gross, L., Qian, R., and Chandra, S. (2021, January 25\u201328). Industry-Scale IR-Based Bug Localization: A Perspective from Facebook. Proceedings of the 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP 2021), Madrid, Spain.","DOI":"10.1109\/ICSE-SEIP52600.2021.00028"},{"key":"ref_20","unstructured":"Shao, S., and Yu, T. (2024). Enhancing IR-Based Fault Localization Using Large Language Models. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/s10515-025-00573-x","article-title":"Multi-View Adaptive Contrastive Learning for Information Retrieval Based Fault Localization","volume":"33","author":"Zhou","year":"2026","journal-title":"Autom. Softw. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lou, Y., Zhu, Q., Dong, J., Li, X., Sun, Z., Hao, D., Zhang, L., and Zhang, L. (2021, January 23\u201328). Boosting Coverage-Based Fault Localization via Graph-Based Representation Learning. Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC\/FSE 2021), Athens, Greece.","DOI":"10.1145\/3468264.3468580"},{"key":"ref_23","unstructured":"Li, Y., Tarlow, D., Brockschmidt, M., and Zemel, R. (2016, January 2\u20134). Gated Graph Sequence Neural Networks. Proceedings of the 4th International Conference on Learning Representations (ICLR 2016), San Juan, Puerto Rico."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Meng, X., Wang, X., Zhang, H., Sun, H., Liu, X., and Zhu, L. (2022, January 21\u201329). Improving Fault Localization and Program Repair with Deep Semantic Features and Transferred Knowledge. Proceedings of the 44th International Conference on Software Engineering (ICSE 2022), Pittsburgh, PA, USA.","DOI":"10.1145\/3510003.3510147"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1937","DOI":"10.1145\/3660793","article-title":"Towards Better Graph Neural Network-Based Fault Localization Through Enhanced Code Representation","volume":"1","author":"Rafi","year":"2024","journal-title":"Proc. ACM Softw. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Yang, A.Z.H., Le Goues, C., Martins, R., and Hellendoorn, V.J. (2024, January 14\u201320). Large Language Models for Test-Free Fault Localization. Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering (ICSE 2024), Lisbon, Portugal.","DOI":"10.1145\/3597503.3623342"},{"key":"ref_28","unstructured":"Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Wang, J., Zhang, C., Wang, Z., Yau, S., and Lin, Z. (2024, January 7\u201311). MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework. Proceedings of the International Conference on Learning Representations (ICLR 2024), Vienna, Austria."},{"key":"ref_29","unstructured":"Yu, X., Torbunov, D., Mandal, S., and Ren, Y. (2026). AutoSizer: Automatic Sizing of Analog and Mixed-Signal Circuits via Large Language Model (LLM) Agents. arXiv."},{"key":"ref_30","unstructured":"Arora, D., Sonwane, A., Wadhwa, N., Mehrotra, A., Utpala, S., Bairi, R., Kanade, A., and Natarajan, N. (2024). MASAI: Modular Architecture for Software-Engineering AI Agents. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Yang, J., Jimenez, C.E., Wettig, A., Lieret, K., Yao, S., Narasimhan, K., and Press, O. (2024). SWE-Agent: Agent-Computer Interfaces Enable Automated Software Engineering. Advances in Neural Information Processing Systems 37 (NeurIPS 2024), Curran Associates, Inc.","DOI":"10.52202\/079017-1601"},{"key":"ref_32","unstructured":"Xia, C.S., Deng, Y., Dunn, S., and Zhang, L. (2024). Agentless: Demystifying LLM-Based Software Engineering Agents. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Xiao, Y.A., Gao, P., Peng, C., and Xiong, Y. (2025). Reducing Cost of LLM Agents with Trajectory Reduction. arXiv.","DOI":"10.1145\/3797084"},{"key":"ref_34","unstructured":"Packer, C., Wooders, S., Lin, K., Fang, V., Patil, S.G., Stoica, I., and Gonzalez, J.E. (2023). MemGPT: Towards LLMs as Operating Systems. arXiv."},{"key":"ref_35","unstructured":"Google (2026, May 01). syzbot: Continuous Fuzzing of the Linux Kernel. Available online: https:\/\/syzkaller.appspot.com."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4129\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T01:00:30Z","timestamp":1782867630000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4129"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":35,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26134129"],"URL":"https:\/\/doi.org\/10.3390\/s26134129","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}