Trust-Aware Agentic RAG: A Hybrid Vector-Graph Architectural Framework for Regulated AI Systems

Abstract

Retrieval-augmented generation (RAG) architectures have become central to large language model (LLM) deployment in regulated domains; however, persistent challenges around trust, auditability, and compliance limit their suitability for high-stakes decision support. Prior studies highlight that opaque retrieval chains, probabilistic reasoning, and weak provenance tracking contribute to trust deficits and hallucination risks in RAG-based systems. To address these limitations, this work proposes a trust-aware agentic hybrid architecture that integrates vector-based retrieval with explicit knowledge graph (KG) reasoning, enabling structured constraint enforcement alongside semantic retrieval. The methodology combines architectural system-level design with comparative analysis against conventional RAG pipelines and conceptual validation across regulated use-case scenarios. By leveraging KGs for deterministic reasoning, provenance anchoring, and policy encoding, the hybrid approach is designed to improve traceability of model outputs, reduce hallucination susceptibility, and enhance compliance reasoning compared to vector-only RAG systems. The analysis suggests that agentic orchestration over hybrid retrieval modalities provides a viable pathway toward trustworthy and auditable AI systems. This work contributes a conceptual and architectural foundation for deploying compliant RAG-based AI in regulated environments such as healthcare, finance, and governance, where accountability and explainability are nonnegotiable requirements.