返回全部动态
MITRE-SAGE：多智能体网络安全问答模型
原标题：MITRE-SAGE: A Multi-Agent Cybersecurity Question-Answering model
AI 摘要
MITRE-SAGE 是一个多智能体检索增强生成框架，用于网络安全问答，通过整合语义和结构知识提升 LLM 的可靠性和可解释性。该框架在八个基准任务中的五个上优于独立 LLM 和传统 RAG 方法，并发布了包含 3000 个问答对的 MITRE-QA 基准。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
MITRE-SAGE: A Multi-Agent Cybersecurity Question-Answering model Abstract Effective cybersecurity operations require timely and accurate analysis of large-scale heterogeneous security information; however, analysts increasingly struggle with information overload, alert fatigue, and time-constrained decision-making. Although large language models (LLMs) have demonstrated promising capabilities for question answering (QA), their effectiveness in cybersecurity remains limited by insufficient domain
发布时间：2026-08-19 12:00
抓取时间：2026-08-19 12:39
来源机构：arXiv