Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection
Proceedings of the ACM on Software Engineering · 30.06.2026 · 3 (FSE) · 4323-4346
DOI: 10.1145/3808197 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Software Engineering, online erschienen am 30.06.2026. Verfasst von Xin Peng und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China.
Abstract (Originalsprache)
Automated vulnerability detection is crucial for enhancing software security by identifying potential flaws that attackers could exploit, thereby reducing the reliance on labor-intensive manual code audits. Recent advancements have shifted towards leveraging large language models (LLMs) for vulnerability detection, with techniques like Vul-RAG and VulnSage demonstrating progress through structured prompting and external knowledge integration. However, these approaches typically rely on a single reasoning paradigm, limiting their ability to address the complex and diverse nature of real-world vulnerabilities. To overcome these limitations, we propose ReasonVul, a novel multi-perspective reasoning framework that harnesses cognitive synergy among three specialized LLM agents, each embodying a distinct reasoning mode. The framework begins with independent analyses of the source code, followed by a structured debate mechanism to resolve conflicts through iterative rebuttal and revision, ultimately converging on a collaborative judgment. Evaluated on the PrimeVul dataset, ReasonVul achieves a PairAcc of 40.00% and an F1-score of 72.52%, surpassing the best baseline by 81.24% in PairAcc. Further tests on the JITVUL dataset confirm its generalizability, with a PairAcc of 28.67%. Additionally, we analyzed 542 conflict cases and found that 389 were correctly resolved, highlighting the framework's ability to uncover hidden vulnerabilities through the error-correction mechanism driven by the debate. This work emphasizes the importance of multi-perspective reasoning and collaborative validation in achieving robust and comprehensive vulnerability detection in real-world software systems.
Förderung
- National Key R&D Program of China
Zitieren
APA
Peng, X., Lin, B., Wang, J., Li, X., Ma, J., Yu, J., Mao, X., & Wang, S. (2026). Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection. Proceedings of the ACM on Software Engineering, 3(FSE), 4323-4346. https://doi.org/10.1145/3808197
Vancouver
Peng X, Lin B, Wang J, Li X, Ma J, Yu J, et al. Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection. Proceedings of the ACM on Software Engineering. 2026;3(FSE):4323-4346. doi:10.1145/3808197
BibTeX
@article{Peng2026,
author = {Peng, Xin and Lin, Bo and Wang, Jing and Li, Xiaoling and Ma, Jun and Yu, Jie and Mao, Xiaoguang and Wang, Shangwen},
title = {Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection},
journal = {Proceedings of the ACM on Software Engineering},
year = {2026},
volume = {3},
number = {FSE},
pages = {4323--4346},
doi = {10.1145/3808197}
}
EUVIMED