Awesome Large Language Models for Vulnerability Detection
A continuously updated, curated index of research papers, projects and agent skills on using large language models to detect software vulnerabilities, spanning function-level, repository-level, agentic and smart-contract detection.
This is a curated list of papers, projects and agent skills on using LLMs for vulnerability detection and discovery. It focuses on work from 2025 onward, with a separate archive for earlier papers, and each entry links the paper, its venue and year, and, where available, an accompanying code repository.
Topics covered include benchmarking coding agents on repository-level vulnerability detection, retrieval-augmented and multi-agent detection approaches, fine-tuned models for vulnerability reasoning, and empirical studies of how well general-purpose LLMs find real vulnerabilities at project scale. It is maintained as an open, community-curated index under the MIT license.