RL–LLMfuzzer: reinforcement learning–guided dual–model differential fuzzing for compiler testing
Journal of King Saud University Computer and Information Sciences · 2026-09 · 38 (7)
DOI: 10.1007/s44443-026-01115-5 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 17.08.2026. Verfasst von Donghui Li und 6 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Natural Science Foundation of Henan Province, the Open Fund of Advanced Computing and Intelligent Engineering Laboratory.
Abstract (Originalsprache)
Compiler fuzzing faces a fundamental dilemma: traditional rule-based generators easily fall into coverage bottlenecks due to rigid grammar constraints, while Large Language Models (LLMs), despite synthesizing semantically rich code, suffer from extremely low validity rates in their raw outputs, causing a severe waste of inference resources. To resolve this contradiction, this paper proposes RL-LLMfuzzer, a reinforcement learning and LLM-based differential fuzzing framework. The core innovation lies in its pioneering dual-model decoupled architecture: it utilizes a Multi-Armed Bandit (MAB) algorithm to drive a high-capacity prompt evolution model, dynamically optimizing high-level testing intents based on coverage feedback; subsequently, a local code generation model instantiates these intents. To overcome the inherent syntactic fragility and inference latency of LLMs, the framework integrates a lightweight heuristic repair module and a deterministic AST mutation engine, structurally amplifying valid seeds before differential evaluation. Extensive experiments on GCC and Clang demonstrate superior testing efficacy: verified across multiple independent 24-hour trials, RL-LLMfuzzer achieved a statistically significant 32.1% increase in average compiler backend line coverage in the C-language benchmark compared to the state-of-the-art LLM fuzzer Fuzz4All (p
Förderung
- Natural Science Foundation of Henan Province
- the Open Fund of Advanced Computing and Intelligent Engineering Laboratory
Zitieren
APA
Li, D., Li, Y., Zhao, B., Xu, J., Yao, J., Wang, N., & Liu, L. (2026). RL–LLMfuzzer: reinforcement learning–guided dual–model differential fuzzing for compiler testing. Journal of King Saud University Computer and Information Sciences, 38(7). https://doi.org/10.1007/s44443-026-01115-5
Vancouver
Li D, Li Y, Zhao B, Xu J, Yao J, Wang N, et al. RL–LLMfuzzer: reinforcement learning–guided dual–model differential fuzzing for compiler testing. Journal of King Saud University Computer and Information Sciences. 2026;38(7). doi:10.1007/s44443-026-01115-5
BibTeX
@article{Li2026,
author = {Li, Donghui and Li, Yingying and Zhao, Bo and Xu, Jinlong and Yao, Jinyang and Wang, Nan and Liu, Lili},
title = {RL–LLMfuzzer: reinforcement learning–guided dual–model differential fuzzing for compiler testing},
journal = {Journal of King Saud University Computer and Information Sciences},
year = {2026},
volume = {38},
number = {7},
doi = {10.1007/s44443-026-01115-5}
}
EUVIMED