Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.18153 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917507888054272 |
|---|---|
| author | Peng, Xin Lin, Bo Wang, Jing Li, Xiaoling Ma, Jun Yu, Jie Mao, Xiaoguang Wang, Shangwen |
| author_facet | Peng, Xin Lin, Bo Wang, Jing Li, Xiaoling Ma, Jun Yu, Jie Mao, Xiaoguang Wang, Shangwen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_18153 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection Peng, Xin Lin, Bo Wang, Jing Li, Xiaoling Ma, Jun Yu, Jie Mao, Xiaoguang Wang, Shangwen Software Engineering 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. |
| title | Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2605.18153 |