RADIANT-LLM: an Agentic Retrieval Augmented Generation Framework for Reliable Decision Support in Safety-Critical Nuclear Engineering

TL;DR

RADIANT-LLM is a retrieval-augmented framework designed for nuclear safety applications, improving factual accuracy and reducing hallucinations in LLMs through domain-specific retrieval, provenance tracking, and human validation.

Contribution

The paper introduces RADIANT-LLM, a multi-modal, domain-aware RAG framework with provenance enforcement tailored for nuclear engineering decision support.

Findings

High domain-specific retrieval accuracy (85-98%) across knowledge base sizes.

Significantly lower hallucination rates compared to general-purpose LLMs.

Enhanced transparency and traceability in LLM responses for safety-critical tasks.

Abstract

Reliable decision support in nuclear engineering requires traceable, domain-grounded knowledge retrieval, yet safety and risk analysis workflows remain hampered by fragmented documentation and hallucination when use pre-trained large language model (LLM) in specialized nuclear domains. To address these challenges, this paper presents RADIANT-LLM (Retrival-Augumented, Domain-Intelligent Agent for Nuclear Technologies using LLM), a multi-modal retrieval-augmented generation (RAG) framework designed for nuclear safety, security, and safeguards applications. The framework uses a local-first, model-agnostic architecture that pairs a multi-modal document ingestion pipeline with a structured, metadata-rich knowledge base, supporting page- and figure-level retrieval from technical documents. An agentic layer coordinates domain-specific tools, enforces citation-backed responses with provenance tracking, and supports human-in-the-loop validation to reduce hallucination risks. To rigorously evaluate this framework, we develop and apply a suite of domain-aware metrics, including Context Precision (CoP), Hallucination Rate (HR), and Visual Recall (ViR), to expert-curated benchmarks derived from Used Nuclear Fuel Storage Facility design guidance. Across varying knowledge base sizes, CoP and ViR remain within an 85--98\% band, and hallucination rates are substantially lower than those observed in general-purpose deployments. When the same queries are posed to commercial LLM platforms without the RAG layer, hallucinations and citation errors increase markedly. These results indicate that a locally controlled, multi-modal RAG framework with domain-specific retrieval and provenance enforcement is necessary to achieve the factual accuracy, transparency, and auditability that nuclear engineering workflows demand.