CRAIDec 8, 2025

VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection

arXiv:2512.07533v17 citationsh-index: 8Has Code
Originality Highly original
AI Analysis

This work addresses software security vulnerabilities for developers and security analysts, representing a pioneering effort in AI-driven project-level detection.

The authors tackled the problem of vulnerability detection in software by developing VulnLLM-R, a specialized reasoning LLM, which outperformed state-of-the-art static analysis tools and other large reasoning models across multiple programming languages, discovering zero-day vulnerabilities in real-world projects.

We propose VulnLLM-R, the~\emph{first specialized reasoning LLM} for vulnerability detection. Our key insight is that LLMs can reason about program states and analyze the potential vulnerabilities, rather than simple pattern matching. This can improve the model's generalizability and prevent learning shortcuts. However, SOTA reasoning LLMs are typically ultra-large, closed-source, or have limited performance in vulnerability detection. To address this, we propose a novel training recipe with specialized data selection, reasoning data generation, reasoning data filtering and correction, and testing-phase optimization. Using our proposed methodology, we train a reasoning model with seven billion parameters. Through extensive experiments on SOTA datasets across Python, C/C++, and Java, we show that VulnLLM-R has superior effectiveness and efficiency than SOTA static analysis tools and both open-source and commercial large reasoning models. We further conduct a detailed ablation study to validate the key designs in our training recipe. Finally, we construct an agent scaffold around our model and show that it outperforms CodeQL and AFL++ in real-world projects. Our agent further discovers a set of zero-day vulnerabilities in actively maintained repositories. This work represents a pioneering effort to enable real-world, project-level vulnerability detection using AI agents powered by specialized reasoning models. The code is available at~\href{https://github.com/ucsb-mlsec/VulnLLM-R}{github}.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes