Large Language Models (LLMs) have demonstrated remarkable capabilities across various cybersecurity tasks, including vulnerability classification, detection, and patching. However, their potential in automated vulnerability report documentation and analysis remains underexplored. We present RAVEN (Retrieval Augmented Vulnerability Exploration Network), a framework leveraging LLM agents and Retrieval Augmented Generation (RAG) to synthesize comprehensive vulnerability analysis reports. Given vulnerable source code, RAVEN generates reports following the Google Project Zero Root Cause Analysis template. The framework uses four modules: an Explorer agent for vulnerability identification, a RAG engine retrieving relevant knowledge from curated databases including Google Project Zero reports and CWE entries, an Analyst agent for impact and exploitation assessment, and a Reporter agent for structured report generation. To ensure quality, RAVEN includes a task specific LLM Judge evaluating reports across structural integrity, ground truth alignment, code reasoning quality, and remediation quality. We evaluate RAVEN on 105 vulnerable code samples covering 15 CWE types from the NIST-SARD dataset. Results show an average quality score of 54.21%, supporting the effectiveness of our approach for automated vulnerability documentation.

翻译：大型语言模型（LLMs）已在包括漏洞分类、检测和修复在内的多种网络安全任务中展现出卓越能力。然而，它们在自动化漏洞报告文档编制与分析方面的潜力尚未得到充分探索。本文提出RAVEN（检索增强型漏洞探索网络），一个利用LLM智能体与检索增强生成（RAG）技术合成综合漏洞分析报告的框架。给定存在漏洞的源代码，RAVEN遵循Google Project Zero根因分析模板生成报告。该框架包含四个模块：用于漏洞识别的探索器智能体、用于从包含Google Project Zero报告和CWE条目的精选数据库中检索相关知识的RAG引擎、用于影响与可利用性评估的分析器智能体，以及用于结构化报告生成的报告器智能体。为确保质量，RAVEN包含一个任务特定的LLM评判器，评估报告的结构完整性、真实答案对齐度、代码推理质量及修复质量。我们在来自NIST-SARD数据集的105个涵盖15种CWE类型的含漏洞代码样本上评估了RAVEN。结果显示平均质量得分为54.21%，验证了所提方法用于自动化漏洞文档编制的有效性。