AutoPatch: Multi-Agent Framework for Patching Real-World CVE Vulnerabilities

TL;DR

AutoPatch is a multi-agent framework that effectively patches real-world CVE vulnerabilities in LLM-generated code by combining retrieval, analysis, and reasoning, achieving high accuracy and cost efficiency.

Contribution

It introduces AutoPatch, a novel multi-agent system integrating retrieval, analysis, and reasoning to patch complex vulnerabilities without costly fine-tuning.

Findings

90.4% accuracy in CVE matching

89.5% F1-score for vulnerability verification

95.0% accuracy in patching

Abstract

Large Language Models (LLMs) have emerged as promising tools in software development, enabling automated code generation and analysis. However, their knowledge is limited to a fixed cutoff date, making them prone to generating code vulnerable to newly disclosed CVEs. Frequent fine-tuning with new CVE sets is costly, and existing LLM-based approaches focus on oversimplified CWE examples and require providing explicit bug locations to LLMs, limiting their ability to patch complex real-world vulnerabilities. To address these limitations, we propose AutoPatch, a multi-agent framework designed to patch vulnerable LLM-generated code, particularly those introduced after the LLMs' knowledge cutoff. AutoPatch integrates Retrieval-Augmented Generation (RAG) with a structured database of recently disclosed vulnerabilities, comprising 525 code snippets derived from 75 high-severity CVEs across real-world systems such as the Linux kernel and Chrome. AutoPatch combines semantic and taint analysis to identify the most relevant CVE and leverages enhanced Chain-of-Thought (CoT) reasoning to construct enriched prompts for verification and patching. Our unified similarity model, which selects the most relevant vulnerabilities, achieves 90.4 percent accuracy in CVE matching. AutoPatch attains 89.5 percent F1-score for vulnerability verification and 95.0 percent accuracy in patching, while being over 50x more cost-efficient than traditional fine-tuning approaches.