SCAIR：用于企业知识图谱的模式条件代理迭代推理
SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs
- University of Stuttgart（斯图加特大学）
- Bosch Center for AI（博世人工智能中心）
- University of Oslo（奥斯陆大学）
- University of Southampton（南安普顿大学）
- BSH Home Applications Holding (China) Co., Ltd（博西华家用电器有限公司（中国））
- Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对现有方法在企业知识图谱应用的局限，提出SCAIR无训练框架，集成结构化规划与受控迭代推理，通过模式条件结构先验等提升性能，强调企业图推理要结合领域约束，与业务逻辑对齐可增效。
AI中文摘要：
基于知识图谱的检索增强生成（KG-RAG）实现了与结构化企业知识的自然语言交互，但在公共基准上表现良好的现有代理方法往往无法推广到真实世界的企业知识图谱，这些图谱密集、由模式驱动且有操作限制。为解决这些限制，我们提出SCAIR（模式条件代理迭代推理），一个无训练框架，通过注入模式条件结构先验并在多跳推理中强制模式感知遍历，将结构化规划与受控迭代推理集成。在从真实世界配置管理数据库（CMDB）构建的面向企业的基准上的实验表明，SCAIR比现有KG-RAG方法显著提高了性能。关键的是，我们的研究强调可靠的企业图推理不能依赖通用代理设计；相反，必须将目标领域的结构和操作约束明确纳入推理过程。我们证明通过使代理设计与业务逻辑一致，无需昂贵的模型重新训练就能实现显著的性能提升。
英文摘要：
Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) enables natural language interaction with structured enterprise knowledge, yet existing agentic approaches that perform well on public benchmarks often fail to generalize to real-world enterprise Knowledge Graphs (KGs), which are dense, schema-driven, and operationally constrained. To address these limitations, we propose SCAIR (Schema-Conditioned Agentic Iterative Reasoning), a training-free framework that integrates structured planning with controlled iterative reasoning by injecting schema-conditioned structural priors and enforcing schema-aware traversal during multi-hop reasoning. Experiments on an enterprise-oriented benchmark constructed from a real-world Configuration Management DataBase (CMDB) demonstrate that SCAIR substantially improves performance over existing KG-RAG methods. Crucially, our study highlights that reliable enterprise graph reasoning cannot rely on generic agentic designs; instead, it must explicitly incorporate the target domain's structural and operational constraints into the reasoning process. We demonstrate that by aligning agent design with business logic, substantial performance gains can be achieved without the need for costly model retraining.
