Probabilistic Agents in Deterministic Audits: Evaluating Multi-Agent Systems for Automated Audits Based on the German IT-Grundschutz
确定性审计中的概率性智能体:基于德国IT-Grundschutz的自动化审计多智能体系统评估
机构 * Department of Mathematics and Computer Science(数学与计算机科学系) ; Freie Universität Berlin(柏林自由大学)
专题命中 评测与基准 :LLM(summary_cn,abstract_cn);分类 cs.AI
AI总结 提出结合混合检索增强生成的多智能体系统架构,通过假设验证循环和解耦推理流水线部分自动化IT-Grundschutz认证,实验表明在语义任务上高效但在逻辑推理阶段受限于LLM的概率性。
Comments Accepted for publication at the 2026 IEEE International Systems Conference (SysCon), Halifax, NS, Canada, April 6-9, 2026. 8 pages, 1 figure