一作ACL 2026Findings· Findings of ACL
V ul A gent: Hypothesis-Validation Driven Multi-Agent Architecture for Vulnerability Detection
Ziliang Wang · Ge Li · Jia Li · Hao Zhu · Zhi Jin
摘要
Vulnerability detection with language models is challenging: it requires (i) precisely localizing security-sensitive code and (ii) reasoning about potential vulnerability conditions under complex, partially observed program context. We present VulAgent, a multi-agent vulnerability detection frame...