SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs
For practitioners deploying KG-RAG in enterprise settings with dense, schema-driven knowledge graphs, SCAIR provides a practical solution that outperforms generic agentic approaches by incorporating domain-specific structural constraints.
SCAIR proposes a training-free framework that integrates schema-conditioned structural priors and schema-aware traversal for multi-hop reasoning on enterprise knowledge graphs. On a real-world CMDB benchmark, it substantially improves performance over existing KG-RAG methods without requiring model retraining.
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.