analiza aiqbench
This research introduces SCAIR, a training-free framework designed to enhance agentic reasoning within dense enterprise knowledge graphs by explicitly incorporating schema constraints. By aligning agent design with specific business logic rather than relying on generic models, the approach achieves significant performance gains in multi-hop reasoning tasks without costly retraining. This work underscores that effective AI deployment in operational environments requires adapting structural priors to domain-specific graph architectures.
SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs
arXiv:2607.22571v1 Announce Type: new Abstract: 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.
Abstract: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.
Artificial Intelligence (cs.AI)
arXiv:2607.22571 [cs.AI]
(or arXiv:2607.22571v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2607.22571 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 243 cuvinte
Subiecte conexe
Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic
Hugging Face · 1 iun. 2026
Prompt Engineering vs Loop Engineering vs Graph Engineering: What Changes at Each Layer
MarkTechPost · 30 iul. 2026
Market surveillance agent with LangGraph and Strands on AgentCore
AWS · 28 iul. 2026
How Trane gets building insights 60x faster with Amazon Bedrock AgentCore
AWS · 22 sept. 2026