---
title: "Taming System Complexity — paper by Zhou et al. (2026)"
description: "To address this, the authors propose LinuxFL+, a plug-in framework that widens agents' candidate lists in two ways: through… 41 references."
authors: ["Zhenhao Zhou", "Zhuochen Huang", "Yike He", "Chong Wang", "Jiajun Wang", "Yijian Wu", "Xin Peng", "Yiling Lou"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.862/"
doi: "10.18653/v1/2026.acl-long.862"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhou-2026-taming-system-complexity-demystifying-software/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhou-2026-taming-system-complexity-demystifying-software/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/18/) / Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults

# Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults

**Authors:** [Zhenhao Zhou](https://md.research.elamur.ai/free/en/authors/zhenhao-zhou/), Zhuochen Huang, Yike He, [Chong Wang](https://md.research.elamur.ai/free/en/authors/chong-wang/), Jiajun Wang, Yijian Wu, Xin Peng and Yiling Lou · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.862/) · [PDF](https://aclanthology.org/2026.acl-long.862.pdf) · [DOI 10.18653/v1/2026.acl-long.862](https://doi.org/10.18653/v1/2026.acl-long.862) · [OpenAlex](https://openalex.org/W4414586747)

**Citations:** 1 citations (OpenAlex, 2026-10-14)

## Summary
LLM agents locate buggy files well on moderate-size Python projects such as SWE-bench, but it was unclear whether this holds for the Linux kernel. The kernel is harder: its codebase is huge, runtime observability is limited, and hardware and timing factors vary widely. The authors built LinuxFLBench, a fault localization benchmark of 250 real kernel bugs. They started from user reports in Kernel.org Bugzilla, kept only fixed bugs with a single-file patch, and manually reviewed the result. Testing SWE-Agent, AutoCodeRover and Agentless on it showed much weaker file-level accuracy than on SWE-bench. Failure analysis found that agents often skipped related files or did not cover the full root cause. To address this, the authors propose LinuxFL+, a plug-in framework that widens agents' candidate lists in two ways: through the repository's directory structure and through likely causes drawn from the Linux kernel mailing list (LKML). It raised accuracy for every agent tested at little extra cost. The work offers a realistic testbed for diagnosing faults in very large systems.

## Key points
- **LinuxFLBench construction:** the authors filtered 2,138 Bugzilla reports (collected up to end of 2024) to 635 single-file cases, then manually curated them to 250 tasks. These span more than 120 kernel versions and 66 components. Codebases are 10–30× larger than in SWE-bench, and bug reports are about 1.5× longer.
- **Baseline agent performance:** with GPT-4o as the backbone, existing agents reached only 36.8–41.6% top-1 file-level accuracy. That is 16.7–31.9 points lower than their SWE-bench results.
- **LinuxFL+ design and gains:** the framework combines directory-aware expansion with potential cause expansion based on LKML. It improved all agents by 7.2–11.2% in accuracy, and an ablation study confirmed that each strategy contributes.
- **Gains on hard cases:**
  - For performance-issue bugs, MRR rose from 0.165 to 0.458.
  - For reports with no explicit file hints, MRR rose from 0.300 to 0.427.
  - Method-level Recall@10 improved by more than 0.09 for all agents.
- **Availability:** data and code are released at github.com/FudanSELab/LinuxFLBench. Additional LLMs, such as Qwen3-32B, were also briefly tested.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Fudan University](https://md.research.elamur.ai/free/en/universities/fudan-university/) — University, Shanghai, China · 167 works · 20,987 citations
- [Nanyang Technological University](https://md.research.elamur.ai/free/en/universities/nanyang-technological-university/) — University, Singapore, Singapore · 156 works · 25,644 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works · [💻 Software](https://md.research.elamur.ai/free/en/shelves/computer-science/software/) · 92 works · [🌐 Computer Networks and Communications](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-networks-and-communications/) · 64 works

🧭 Topics (1): [💻 Code & programming languages](https://md.research.elamur.ai/free/en/topics/code-and-programming/) · 129 works

## Cite

Cite as: Zhenhao Zhou, Zhuochen Huang, Yike He, Chong Wang, Jiajun Wang, Yijian Wu, Xin Peng and Yiling Lou. 2026. Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhou2026taming,
  title = {{Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults}},
  author = {Zhenhao Zhou, Zhuochen Huang, Yike He, Chong Wang, Jiajun Wang, Yijian Wu, Xin Peng and Yiling Lou},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.862},
  url = {https://doi.org/10.18653/v1/2026.acl-long.862}
}
```

- [← previous TamilVoiceLab@DravidianLangTech 2026: Investigating Whisper Tamil Large-v2 for Dialectal Tamil Speech Recognition](https://md.research.elamur.ai/free/en/papers/priya-2026-tamilvoicelab-dravidianlangtech-2026-investigating-whisper/)
- [next → TaoType: Predicting Fine-Grained Typing Intent for Faster Search](https://md.research.elamur.ai/free/en/papers/yu-2026-taotype-predicting-fine-grained-typing/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/18/)

## References

41 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Rui Abreu, Peter Zoeteweij, and Arjan J. C. van Gemund. 2006. An evaluation of similarity coefficients for software fault localization. In 12th IEEE Pacific Rim International Symposium on Dependable Computing (PRDC 2006), 18-20 December, 2006, University of California, Riverside, USA, pages 39– 46.… [find](https://scholar.google.com/scholar?q=Rui+Abreu%2C+Peter+Zoeteweij%2C+and+Arjan+J%2E+C%2E+van+Gemund%2E+2006%2E+An+evaluation+of+similarity+coefficients+for+software+fault+localization%2E+In+12th+IEEE+Pacific+Rim+International+Symposium+on+Dependable+C)
2. Abdulaziz Alaboudi and Thomas D. LaToza. 2023. Hypothesizer: A hypothesis-based debugger to find and test debugging hypotheses. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, UIST 2023, San Francisco, CA, USA, 29 October 2023- 1 November 2023, pages 73:1–7… [find](https://scholar.google.com/scholar?q=Abdulaziz+Alaboudi+and+Thomas+D%2E+LaToza%2E+2023%2E+Hypothesizer%3A+A+hypothesis%2Dbased+debugger+to+find+and+test+debugging+hypotheses%2E+In+Proceedings+of+the+36th+Annual+ACM+Symposium+on+User+Interface+Softwa)
3. Tegawendé F. Bissyandé, Laurent Réveillère, Julia Lawall, and Gilles Muller. 2012. Diagnosys: automatic generation of a debugging interface to the linux kernel. In IEEE/ACM International Conference on Automated Software Engineering, ASE’12, Essen, Germany, September 3-7, 2012, pages 60–69. ACM. [find](https://scholar.google.com/scholar?q=Tegawend%C3%A9+F%2E+Bissyand%C3%A9%2C+Laurent+R%C3%A9veill%C3%A8re%2C+Julia+Lawall%2C+and+Gilles+Muller%2E+2012%2E+Diagnosys%3A+automatic+generation+of+a+debugging+interface+to+the+linux+kernel%2E+In+IEEE%2FACM+International+Conference+on)
4. Martin Bligh and Andy P Whitcroft. 2006. Fully automated testing of the linux kernel. In Proceedings of the Linux Symposium, volume 1, pages 113–125. Citeseer. [find](https://scholar.google.com/scholar?q=Martin+Bligh+and+Andy+P+Whitcroft%2E+2006%2E+Fully+automated+testing+of+the+linux+kernel%2E+In+Proceedings+of+the+Linux+Symposium%2C+volume+1%2C+pages+113%E2%80%93125%2E+Citeseer%2E)
5. Yu Chen, Fengguang Wu, Kuanlong Yu, Lei Zhang, Yuheng Chen, Yang Yang, and Junjie Mao. 2013. Instant bug testing service for linux kernel. In 10th IEEE International Conference on High Performance Computing and Communications & 2013 IEEE International Conference on Embedded and Ubiquitous Computing,… [find](https://scholar.google.com/scholar?q=Yu+Chen%2C+Fengguang+Wu%2C+Kuanlong+Yu%2C+Lei+Zhang%2C+Yuheng+Chen%2C+Yang+Yang%2C+and+Junjie+Mao%2E+2013%2E+Instant+bug+testing+service+for+linux+kernel%2E+In+10th+IEEE+International+Conference+on+High+Performance+Com)
6. Zhaoling Chen, Xiangru Tang, Gangda Deng, Fang Wu, Jialong Wu, Zhiwei Jiang, Viktor K. Prasanna, Dae R. Jeong, Minkyu Jung, Yoochan Lee, Byoungyoung Lee, Insik Shin, and Youngjin Kwon. 2023. Diagnosing kernel concurrency failures with AITIA. In Proceedings of the Eighteenth European Conference on Co… [find](https://scholar.google.com/scholar?q=Zhaoling+Chen%2C+Xiangru+Tang%2C+Gangda+Deng%2C+Fang+Wu%2C+Jialong+Wu%2C+Zhiwei+Jiang%2C+Viktor+K%2E+Prasanna%2C+Dae+R%2E+Jeong%2C+Minkyu+Jung%2C+Yoochan+Lee%2C+Byoungyoung+Lee%2C+Insik+Shin%2C+and+Youngjin+Kwon%2E+2023%2E+Diagnosin)
7. Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R. Narasimhan. 2024. [Swe-bench: Can language models resolve real-world github issues?](https://md.research.elamur.ai/free/en/papers/jimenez-2024-swe-bench-can-language-models/) In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenRe…
8. René Just, Darioush Jalali, and Michael D. Ernst. 2014. Defects4j: a database of existing faults to enable controlled testing studies for java programs. In International Symposium on Software Testing and Analysis, ISSTA ’14, San Jose, CA, USA - July 21 - 26, 2014, pages 437–440. ACM. [find](https://scholar.google.com/scholar?q=Ren%C3%A9+Just%2C+Darioush+Jalali%2C+and+Michael+D%2E+Ernst%2E+2014%2E+Defects4j%3A+a+database+of+existing+faults+to+enable+controlled+testing+studies+for+java+programs%2E+In+International+Symposium+on+Software+Testing+)
9. Sungmin Kang, Gabin An, and Shin Yoo. 2024. A quantitative and qualitative evaluation of llm-based explainable fault localization. Proc. ACM Softw. Eng., 1(FSE):1424–1446. [find](https://scholar.google.com/scholar?q=Sungmin+Kang%2C+Gabin+An%2C+and+Shin+Yoo%2E+2024%2E+A+quantitative+and+qualitative+evaluation+of+llm%2Dbased+explainable+fault+localization%2E+Proc%2E+ACM+Softw%2E+Eng%2E%2C+1%28FSE%29%3A1424%E2%80%931446%2E)
10. Kernel.org. 2025a. Kernel.org Https://bugzilla.kernel.org. bugzilla. [find](https://scholar.google.com/scholar?q=Kernel%2Eorg%2E+2025a%2E+Kernel%2Eorg+Https%3A%2F%2Fbugzilla%2Ekernel%2Eorg%2E+bugzilla%2E)
11. Kernel.org. 2025b. Kernel.org Http://rsync.kernel.org/pub/linux/kernel. rsync. [find](https://scholar.google.com/scholar?q=Kernel%2Eorg%2E+2025b%2E+Kernel%2Eorg+Http%3A%2F%2Frsync%2Ekernel%2Eorg%2Fpub%2Flinux%2Fkernel%2E+rsync%2E)
12. Kernel.org. 2025c. Linux kernel mailing list. Https://lore.kernel.org. [find](https://scholar.google.com/scholar?q=Kernel%2Eorg%2E+2025c%2E+Linux+kernel+mailing+list%2E+Https%3A%2F%2Flore%2Ekernel%2Eorg%2E)
13. Lucas Layman, Madeline Diep, Meiyappan Nagappan, Janice Singer, Robert DeLine, and Gina Venolia. 2013. Debugging revisited: Toward understanding the debugging needs of contemporary software developers. In 2013 ACM / IEEE International Symposium on Empirical Software Engineering and Measurement, Balt… [find](https://scholar.google.com/scholar?q=Lucas+Layman%2C+Madeline+Diep%2C+Meiyappan+Nagappan%2C+Janice+Singer%2C+Robert+DeLine%2C+and+Gina+Venolia%2E+2013%2E+Debugging+revisited%3A+Toward+understanding+the+debugging+needs+of+contemporary+software+developers)
14. Hanzhi Liu, Yanyan Jiang, and Chang Xu. 2025. Understanding the linux kernel, visually. In Proceedings of the Twentieth European Conference on Computer Systems, EuroSys 2025, Rotterdam, The Netherlands, 30 March 2025 - 3 April 2025, pages 1044–1060. ACM. [find](https://scholar.google.com/scholar?q=Hanzhi+Liu%2C+Yanyan+Jiang%2C+and+Chang+Xu%2E+2025%2E+Understanding+the+linux+kernel%2C+visually%2E+In+Proceedings+of+the+Twentieth+European+Conference+on+Computer+Systems%2C+EuroSys+2025%2C+Rotterdam%2C+The+Netherland)
15. Junwei Liu, Kaixin Wang, Yixuan Chen, Xin Peng, Zhenpeng Chen, Lingming Zhang, and Yiling Lou. 2024. Large language model-based agents for software engineering: A survey. CoRR, abs/2409.02977. — [arXiv:2409.02977](https://arxiv.org/abs/2409.02977) [find](https://scholar.google.com/scholar?q=Junwei+Liu%2C+Kaixin+Wang%2C+Yixuan+Chen%2C+Xin+Peng%2C+Zhenpeng+Chen%2C+Lingming+Zhang%2C+and+Yiling+Lou%2E+2024%2E+Large+language+model%2Dbased+agents+for+software+engineering%3A+A+survey%2E+CoRR%2C+abs%2F2409%2E02977%2E+%E2%80%94+%5BarXi)
16. Yiling Lou, Qihao Zhu, Jinhao Dong, Xia Li, Zeyu Sun, Dan Hao, Lu Zhang, and Lingming Zhang. 2021. Boosting coverage-based fault localization via graph-based representation learning. In ESEC/FSE ’21: 29th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software… [find](https://scholar.google.com/scholar?q=Yiling+Lou%2C+Qihao+Zhu%2C+Jinhao+Dong%2C+Xia+Li%2C+Zeyu+Sun%2C+Dan+Hao%2C+Lu+Zhang%2C+and+Lingming+Zhang%2E+2021%2E+Boosting+coverage%2Dbased+fault+localization+via+graph%2Dbased+representation+learning%2E+In+ESEC%2FFSE+%E2%80%9921%3A+)
17. Xing Han Lù. 2024. Bm25s: Orders of magnitude faster lexical search via eager sparse scoring. Preprint, arXiv:2407.03618. — [arXiv:2407.03618](https://arxiv.org/abs/2407.03618) [find](https://scholar.google.com/scholar?q=Xing+Han+L%C3%B9%2E+2024%2E+Bm25s%3A+Orders+of+magnitude+faster+lexical+search+via+eager+sparse+scoring%2E+Preprint%2C+arXiv%3A2407%2E03618%2E+%E2%80%94+%5BarXiv%3A2407%2E03618%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2407%2E03618%29)
18. Alex Mathai, Chenxi Huang, Petros Maniatis, Aleksandr Nogikh, Franjo Ivancic, Junfeng Yang, and Baishakhi Ray. 2024. Kgym: A platform and dataset to benchmark large language models on linux kernel crash resolution. CoRR, abs/2407.02680. — [arXiv:2407.02680](https://arxiv.org/abs/2407.02680) [find](https://scholar.google.com/scholar?q=Alex+Mathai%2C+Chenxi+Huang%2C+Petros+Maniatis%2C+Aleksandr+Nogikh%2C+Franjo+Ivancic%2C+Junfeng+Yang%2C+and+Baishakhi+Ray%2E+2024%2E+Kgym%3A+A+platform+and+dataset+to+benchmark+large+language+models+on+linux+kernel+cra)
19. Samuel Miserendino, Michele Wang, Tejal Patwardhan, and Johannes Heidecke. 2025. Swe-lancer: Can frontier llms earn $1 million from real-world freelance software engineering? CoRR, abs/2502.12115. [find](https://scholar.google.com/scholar?q=Samuel+Miserendino%2C+Michele+Wang%2C+Tejal+Patwardhan%2C+and+Johannes+Heidecke%2E+2025%2E+Swe%2Dlancer%3A+Can+frontier+llms+earn+%241+million+from+real%2Dworld+freelance+software+engineering%3F+CoRR%2C+abs%2F2502%2E12115%2E)
20. Amr Mansour Mohsen, Hesham A. Hassan, Khaled Wassif, Ramadan Moawad, and Soha Makady. 2023. Enhancing bug localization using phase-based approach. IEEE Access, 11:35901–35913. [find](https://scholar.google.com/scholar?q=Amr+Mansour+Mohsen%2C+Hesham+A%2E+Hassan%2C+Khaled+Wassif%2C+Ramadan+Moawad%2C+and+Soha+Makady%2E+2023%2E+Enhancing+bug+localization+using+phase%2Dbased+approach%2E+IEEE+Access%2C+11%3A35901%E2%80%9335913%2E)
21. OpenAI. 2024. Hello gpt-4o. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+Hello+gpt%2D4o%2E)
22. Yihao Qin, Shangwen Wang, Yiling Lou, Jinhao Dong, Kaixin Wang, Xiaoling Li, and Xiaoguang Mao. 2024. Agentfl: Scaling llm-based fault localization to project-level context. CoRR, abs/2403.16362. — [arXiv:2403.16362](https://arxiv.org/abs/2403.16362) [find](https://scholar.google.com/scholar?q=Yihao+Qin%2C+Shangwen+Wang%2C+Yiling+Lou%2C+Jinhao+Dong%2C+Kaixin+Wang%2C+Xiaoling+Li%2C+and+Xiaoguang+Mao%2E+2024%2E+Agentfl%3A+Scaling+llm%2Dbased+fault+localization+to+project%2Dlevel+context%2E+CoRR%2C+abs%2F2403%2E16362%2E+%E2%80%94+%5Ba)
23. Nils Reimers and Iryna Gurevych. 2019. [Sentence-bert: Sentence embeddings using siamese bert-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, Ch…
24. Stephen E. Robertson, Steve Walker, and Micheline Hancock-Beaulieu. 1995. Large test collection experiments on an operational, interactive system: Okapi at TREC. Inf. Process. Manag., 31(3):345–360. [find](https://scholar.google.com/scholar?q=Stephen+E%2E+Robertson%2C+Steve+Walker%2C+and+Micheline+Hancock%2DBeaulieu%2E+1995%2E+Large+test+collection+experiments+on+an+operational%2C+interactive+system%3A+Okapi+at+TREC%2E+Inf%2E+Process%2E+Manag%2E%2C+31%283%29%3A345%E2%80%93360%2E)
25. Ripon K. Saha, Julia Lawall, Sarfraz Khurshid, and Dewayne E. Perry. 2014. On the effectiveness of information retrieval based bug localization for C programs. In 30th IEEE International Conference on Software Maintenance and Evolution, Victoria, BC, Canada, September 29 - October 3, 2014, pages 161… [find](https://scholar.google.com/scholar?q=Ripon+K%2E+Saha%2C+Julia+Lawall%2C+Sarfraz+Khurshid%2C+and+Dewayne+E%2E+Perry%2E+2014%2E+On+the+effectiveness+of+information+retrieval+based+bug+localization+for+C+programs%2E+In+30th+IEEE+International+Conference+on)
26. Ripon K. Saha, Matthew Lease, Sarfraz Khurshid, and Dewayne E. Perry. 2013. Improving bug localization using structured information retrieval. In 2013 28th IEEE/ACM International Conference on Automated Software Engineering, ASE 2013, Silicon Valley, CA, USA, November 11-15, 2013, pages 345–355. IEE… [find](https://scholar.google.com/scholar?q=Ripon+K%2E+Saha%2C+Matthew+Lease%2C+Sarfraz+Khurshid%2C+and+Dewayne+E%2E+Perry%2E+2013%2E+Improving+bug+localization+using+structured+information+retrieval%2E+In+2013+28th+IEEE%2FACM+International+Conference+on+Automat)
27. Lucas Serrano, Van-Anh Nguyen, Ferdian Thung, Lingxiao Jiang, David Lo, Julia Lawall, and Gilles Muller. 2020. SPINFER: inferring semantic patches for the linux kernel. In Proceedings of the 2020 USENIX Annual Technical Conference, USENIX ATC 2020, July 15-17, 2020, pages 235–248. USENIX Association… [find](https://scholar.google.com/scholar?q=Lucas+Serrano%2C+Van%2DAnh+Nguyen%2C+Ferdian+Thung%2C+Lingxiao+Jiang%2C+David+Lo%2C+Julia+Lawall%2C+and+Gilles+Muller%2E+2020%2E+SPINFER%3A+inferring+semantic+patches+for+the+linux+kernel%2E+In+Proceedings+of+the+2020+USEN)
28. Bunyamin Sisman, Shayan A. Akbar, and Avinash C. Kak. 2017. Exploiting spatial code proximity and order for improved source code retrieval for bug localization. J. Softw. Evol. Process., 29(1). [find](https://scholar.google.com/scholar?q=Bunyamin+Sisman%2C+Shayan+A%2E+Akbar%2C+and+Avinash+C%2E+Kak%2E+2017%2E+Exploiting+spatial+code+proximity+and+order+for+improved+source+code+retrieval+for+bug+localization%2E+J%2E+Softw%2E+Evol%2E+Process%2E%2C+29%281%29%2E)
29. SWE-bench. 2025. Swe-bench leaderboards. Https://www.swebench.com/. [find](https://scholar.google.com/scholar?q=SWE%2Dbench%2E+2025%2E+Swe%2Dbench+leaderboards%2E+Https%3A%2F%2Fwww%2Eswebench%2Ecom%2F%2E)
30. The Linux Foundation. 2020. Linux kernel history report 2020. [find](https://scholar.google.com/scholar?q=The+Linux+Foundation%2E+2020%2E+Linux+kernel+history+report+2020%2E)
31. Shaowei Wang and David Lo. 2014. Version history, similar report, and structure: putting them together for improved bug localization. In 22nd International Conference on Program Comprehension, ICPC 2014, Hyderabad, India, June 2-3, 2014, pages 53–63. ACM. [find](https://scholar.google.com/scholar?q=Shaowei+Wang+and+David+Lo%2E+2014%2E+Version+history%2C+similar+report%2C+and+structure%3A+putting+them+together+for+improved+bug+localization%2E+In+22nd+International+Conference+on+Program+Comprehension%2C+ICPC+20)
32. Chu-Pan Wong, Yingfei Xiong, Hongyu Zhang, Dan Hao, Lu Zhang, and Hong Mei. 2014a. Boosting bug-report-oriented fault localization with segmentation and stack-trace analysis. In 30th IEEE International Conference on Software Maintenance and Evolution, Victoria, BC, Canada, September 29 - October 3,… [find](https://scholar.google.com/scholar?q=Chu%2DPan+Wong%2C+Yingfei+Xiong%2C+Hongyu+Zhang%2C+Dan+Hao%2C+Lu+Zhang%2C+and+Hong+Mei%2E+2014a%2E+Boosting+bug%2Dreport%2Doriented+fault+localization+with+segmentation+and+stack%2Dtrace+analysis%2E+In+30th+IEEE+Internationa)
33. W. Eric Wong, Vidroha Debroy, Ruizhi Gao, and Yihao Li. 2014b. The dstar method for effective software fault localization. IEEE Trans. Reliab., 63(1):290– 308. [find](https://scholar.google.com/scholar?q=W%2E+Eric+Wong%2C+Vidroha+Debroy%2C+Ruizhi+Gao%2C+and+Yihao+Li%2E+2014b%2E+The+dstar+method+for+effective+software+fault+localization%2E+IEEE+Trans%2E+Reliab%2E%2C+63%281%29%3A290%E2%80%93+308%2E)
34. Chunqiu Steven Xia, Yinlin Deng, Soren Dunn, and Lingming Zhang. 2024. Agentless: Demystifying llm-based software engineering agents. CoRR, abs/2407.01489. [find](https://scholar.google.com/scholar?q=Chunqiu+Steven+Xia%2C+Yinlin+Deng%2C+Soren+Dunn%2C+and+Lingming+Zhang%2E+2024%2E+Agentless%3A+Demystifying+llm%2Dbased+software+engineering+agents%2E+CoRR%2C+abs%2F2407%2E01489%2E)
35. Xin Xia and David Lo. 2023. Information Retrieval-Based Techniques for Software Fault Localization, pages 365–391. [find](https://scholar.google.com/scholar?q=Xin+Xia+and+David+Lo%2E+2023%2E+Information+Retrieval%2DBased+Techniques+for+Software+Fault+Localization%2C+pages+365%E2%80%93391%2E)
36. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 40 others. 2025a. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). CoRR, abs/2505.09388.
37. Chenyuan Yang, Zijie Zhao, and Lingming Zhang. 2025b. Kernelgpt: Enhanced kernel fuzzing via large language models. In Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, ASPLOS 2025, Rotterdam, Netherlands, 30 Marc… [find](https://scholar.google.com/scholar?q=Chenyuan+Yang%2C+Zijie+Zhao%2C+and+Lingming+Zhang%2E+2025b%2E+Kernelgpt%3A+Enhanced+kernel+fuzzing+via+large+language+models%2E+In+Proceedings+of+the+30th+ACM+International+Conference+on+Architectural+Support+for)
38. John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. 2024. [Swe-agent: Agent-computer interfaces enable automated software engineering](https://md.research.elamur.ai/free/en/papers/yang-2024-swe-agent-agent-computer-interfaces/). CoRR, abs/2405.15793. 2. Description: A human-written description of the bug, which may include various typ…
39. Yuntong Zhang, Haifeng Ruan, Zhiyu Fan, and Abhik Roychoudhury. 2024. Autocoderover: Autonomous program improvement. In Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA 2024, Vienna, Austria, September 16-20, 2024, pages 1592–1604. ACM. 3. Product:… [find](https://scholar.google.com/scholar?q=Yuntong+Zhang%2C+Haifeng+Ruan%2C+Zhiyu+Fan%2C+and+Abhik+Roychoudhury%2E+2024%2E+Autocoderover%3A+Autonomous+program+improvement%2E+In+Proceedings+of+the+33rd+ACM+SIGSOFT+International+Symposium+on+Software+Testing+)
40. Jian Zhou, Hongyu Zhang, and David Lo. 2012. Where should the bugs be fixed? more accurate information retrieval-based bug localization based on bug reports. In 34th International Conference on Software Engineering, ICSE 2012, June 2-9, 2012, Zurich, Switzerland, pages 14–24. IEEE Computer Society.… [find](https://scholar.google.com/scholar?q=Jian+Zhou%2C+Hongyu+Zhang%2C+and+David+Lo%2E+2012%2E+Where+should+the+bugs+be+fixed%3F+more+accurate+information+retrieval%2Dbased+bug+localization+based+on+bug+reports%2E+In+34th+International+Conference+on+Softwa)
41. A.2 A Sample Kernel Bug from L INUX FLB ENCH We collect Linux kernel bugs (as shown in Fig. 6) from the reported and fixed bugs on Kernel.org Bugzilla. For each bug, the key information includes: A.3 Comparison with SWE-bench Lite [find](https://scholar.google.com/scholar?q=A%2E2+A+Sample+Kernel+Bug+from+L+INUX+FLB+ENCH+We+collect+Linux+kernel+bugs+%28as+shown+in+Fig%2E+6%29+from+the+reported+and+fixed+bugs+on+Kernel%2Eorg+Bugzilla%2E+For+each+bug%2C+the+key+information+includes%3A+A%2E3+)

*Updated 1 November 2026*