IRAIMar 4

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

arXiv:2604.22755h-index: 3
AI Analysis

For nuclear engineers and safety analysts, this work provides a locally controlled, auditable framework to mitigate hallucination and citation errors in domain-specific knowledge retrieval, addressing a critical bottleneck in high-stakes decision-making.

RADIANT-LLM introduces a multi-modal RAG framework for nuclear engineering that achieves 85-98% context precision and visual recall while substantially reducing hallucination rates compared to general-purpose LLMs, enabling reliable decision support in safety-critical domains.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes