paperJune 2026Unreviewed

Code-Augur: Agentic Vulnerability Detection via Specification Inference

Zhengxiong Luo, Mehtab Zafar, Dylan Wolff, Abhik Roychoudhury

Abstract

The advent of agentic vulnerability detection is already becoming a watershed moment for software security. Audits conducted entirely by autonomous LLM agents are uncovering critical vulnerabilities in fundamental software underpinning digital society. Many of these vulnerabilities remained masked for years, surfacing only now with AI agents. Yet the reasoning behind these discoveries remains alarmingly opaque and unvalidated. What assumptions did the agent make about a function's inputs when it

Cite

@misc{luo2026codeaugur,
  title = {{Code-Augur: Agentic Vulnerability Detection via Specification Inference}},
  author = {Zhengxiong Luo and Mehtab Zafar and Dylan Wolff and Abhik Roychoudhury},
  year = {2026},
  month = jun,
  eprint = {2606.18619},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.18619}
}