EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Arash : Token-Efficient LLM-Assisted Crash Root Cause Analysis in Fuzz Driver Generation

Maoyi Xie, Kaixuan Li, Jingquan Ge, Wei Ma, Yuqiang Sun, Ziqiao Kong, Cen Zhang, Dongge Liu, Oliver Chang, Yang Liu

ACM Transactions on Software Engineering and Methodology · 30.11.2026 · 35 (11) · 1-35

DOI: 10.1145/3811034 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 03.11.2026. Verfasst von Maoyi Xie und 9 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 88 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agency for Science, Technology and Research, Industry Alignment Fund—Industry Collaboration Projects (IAF-ICP) Funding Initiative, cash and in-kind contributions from the industry partne.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fuzz driver generation (FDG) has improved coverage and automation in modern fuzzing. Yet a persistent challenge remains: many crashes in generated drivers stem from incorrect API usage rather than genuine library defects. Consequently, root cause analysis (RCA) becomes essential for distinguishing true library bugs from driver-induced crashes. However, existing FDG systems lack dedicated RCA capabilities, whereas statistical RCA methods, representative of recent top-tier works (e.g., Aurora, Racing, and OptRCA), rely on simplifying assumptions, such as treating the first observable divergence as the true cause, which often fail to capture the underlying fault semantics in practice. In this article, we propose Arash , an RCA framework for fuzz driver crashes that couples semantic checking with token-efficient code slicing to enable precise and efficient analysis. Arash introduces two complementary components: (i) Fuzz Driver–Oriented Checker , which captures two dominant classes of API misuse in the fuzz driver, namely property- and extent-related crashes , and correlates these violations with crash traces and (ii) Parameter-Guided Code Slicing , which reduces token consumption and contextual noise by preserving only statements relevant to parameters involved in the crash. We implement and evaluate Arash across a diverse corpus of fuzz driver crashes. Arash achieves a recall rate of 85.3%, successfully analyzing cases that all other tools fail to handle, and outperforms the current state-of-the-art by 52.6% in diagnostic accuracy. Moreover, Arash is highly token efficient, achieving an average token reduction of 46.8% relative to a large language model (LLM) baseline that consumes windowed raw code context and 24.5% relative to a retrieval-augmented LLM baseline that retrieves full stack–frame functions. Integrated into OSS-Fuzz-Gen, so far 30 genuine library bugs identified by Arash have been confirmed by developers, including one assigned a CVE (CVE-2024-9143), demonstrating its substantial real-world impact in large-scale fuzzing workflows.

Förderung

  • Agency for Science, Technology and Research
  • Industry Alignment Fund—Industry Collaboration Projects (IAF-ICP) Funding Initiative
  • cash and in-kind contributions from the industry partne

Zitieren

APA

Xie, M., Li, K., Ge, J., Ma, W., Sun, Y., Kong, Z., Zhang, C., Liu, D., Chang, O., & Liu, Y. (2026). Arash : Token-Efficient LLM-Assisted Crash Root Cause Analysis in Fuzz Driver Generation. ACM Transactions on Software Engineering and Methodology, 35(11), 1-35. https://doi.org/10.1145/3811034

Vancouver

Xie M, Li K, Ge J, Ma W, Sun Y, Kong Z, et al. Arash : Token-Efficient LLM-Assisted Crash Root Cause Analysis in Fuzz Driver Generation. ACM Transactions on Software Engineering and Methodology. 2026;35(11):1-35. doi:10.1145/3811034

BibTeX
@article{Xie2026,
  author = {Xie, Maoyi and Li, Kaixuan and Ge, Jingquan and Ma, Wei and Sun, Yuqiang and Kong, Ziqiao and Zhang, Cen and Liu, Dongge and Chang, Oliver and Liu, Yang},
  title = {Arash : Token-Efficient LLM-Assisted Crash Root Cause Analysis in Fuzz Driver Generation},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  volume = {35},
  number = {11},
  pages = {1--35},
  doi = {10.1145/3811034}
}
Kostenlos starten →