Interleaving Large Language Models for Compiler Testing
Proceedings of the ACM on Programming Languages · 09.10.2025 · 9 (OOPSLA2) · 815-841
DOI: 10.1145/3763079 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Programming Languages, online erschienen am 09.10.2025. Verfasst von Yunbo Ni und 1 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 43 Literaturangaben.
Abstract (Originalsprache)
Testing compilers with AI models, especially large language models (LLMs), has shown great promise. However, current approaches struggle with two key problems: The generated programs for testing compilers are often too simple, and extensive testing with the LLMs is computationally expensive. In this paper, we propose a novel compiler testing framework that decouples the testing process into two distinct phases: an offline phase and an online phase. In the offline phase, we use LLMs to generate a collection of small but feature-rich code pieces. In the online phase, we reuse these code pieces by strategically combining them to build high-quality and valid test programs, which are then used to test compilers. We implement this idea in a tool, LegoFuzz , for testing C compilers. The results are striking: we found 66 bugs in GCC and LLVM, the most widely used C compilers. Almost half of the bugs are miscompilation bugs, which are serious and hard-to-find bugs that none of the existing LLM-based tools could find. We believe this efficient design opens up new possibilities for using AI models in software testing beyond just C compilers.
Zitieren
APA
Ni, Y., & Li, S. (2025). Interleaving Large Language Models for Compiler Testing. Proceedings of the ACM on Programming Languages, 9(OOPSLA2), 815-841. https://doi.org/10.1145/3763079
Vancouver
Ni Y, Li S. Interleaving Large Language Models for Compiler Testing. Proceedings of the ACM on Programming Languages. 2025;9(OOPSLA2):815-841. doi:10.1145/3763079
BibTeX
@article{Ni2025,
author = {Ni, Yunbo and Li, Shaohua},
title = {Interleaving Large Language Models for Compiler Testing},
journal = {Proceedings of the ACM on Programming Languages},
year = {2025},
volume = {9},
number = {OOPSLA2},
pages = {815--841},
doi = {10.1145/3763079}
}
EUVIMED