Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection

Computer Science > Cryptography and Security [Submitted on 8 Apr 2026] Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection Zi Liang, Qipeng Xie, Jun He, Bohuan Xue, Weizheng Wang, Yuandao Cai, Fei Luo, Boxian Zhang, Haibo Hu, Kaishun Wu Recent advancements in Large Language Models (LLMs) have sparked interest in their application to Static Application Security Testing (SAST), primarily due to their superior contextual reasoning capabilities compared to traditional symbolic or rule-based methods. However, existing LLM-based approaches typically attempt to replace human experts directly without integrating effectively with existing SAST tools. This lack of integration results in ineffectiveness, including high rates of false positives, hallucinations, limited reasoning depth, and excessive token usage, making them impractical for industrial deployment. To overcome these limitations, we present a paradigm shift that reorchestrates the SAST workflow from current LLM-assisted structure to a new LLM-centered workflow. We introduce Argus (Agentic and Retrieval-Augmented Guarding System), the first multi-agent framework designed specifically for vulnerability detection. Argus incorporates three key novelties: comprehensive supply chain analysis, collaborative multi-agent workflows, and the integration of state-of-the-art techniques such as Retrieval-Augmented Generation (RAG) and ReAct to minimize hallucinations and enhance reasoning. Extensive empirical evaluation demonstrates that Argus significantly outperforms existing methods by detecting a higher volume of true vulnerabilities while simultaneously reducing false positives and operational costs. Notably, Argus has identified several critical zero-day vulnerabilities with CVE assignments. Subjects: Cryptography and Security (cs.CR); Computation and Language (cs.CL); Software Engineering (cs.SE) Cite as: arXiv:2604.06633 [cs.CR]   (or arXiv:2604.06633v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.06633 Focus to learn more Submission history From: Zi Liang [view email] [v1] Wed, 8 Apr 2026 03:18:51 UTC (3,162 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.CL cs.SE References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)