AutoSAM: an Agentic Framework for Automating Input File Generation for the SAM Code with Multi-Modal Retrieval-Augmented Generation

2026-03-25

AI Summary

This work addresses the labor-intensive and error-prone process of manually generating input files for thermal-hydraulic simulation codes such as SAM in advanced reactor system design, which requires extracting multimodal data from heterogeneous engineering documents. The study proposes the first framework integrating multimodal retrieval-augmented generation with large language model (LLM) agents to enable end-to-end automated generation of SAM input files directly from unstructured engineering sources—including text, tables, and images—while supporting human-in-the-loop auditing. The approach combines scientific text extraction, visual diagram parsing, semantic embeddings, and domain-specific document processing tools. Evaluated across four test cases of increasing complexity, the method successfully produced executable models in all instances, achieving 100% utilization of structured inputs, approximately 88% accuracy in PDF text extraction, and 100% completeness in geometric information recovery from visual sources.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

In the design and safety analysis of advanced reactor systems, constructing input files for system-level thermal-hydraulics codes such as the System Analysis Module (SAM) remains a labor-intensive task. Analysts must extract and reconcile design data from heterogeneous engineering documents and manually translate it into solver-specific syntax. In this paper, we present AutoSAM, an agentic framework that automates SAM input file generation. The framework combines a large language model agent with retrieval-augmented generation over the solver's user guide and theory manual, together with specialized tools for analyzing PDFs, images, spreadsheets, and text files. AutoSAM ingests unstructured engineering documents, including system diagrams, design reports, and data tables, extracts simulation-relevant parameters into a human-auditable intermediate representation, and synthesizes validated, solver-compatible input decks. Its multimodal retrieval pipeline integrates scientific text extraction, vision-based figure interpretation, semantic embedding, and query answering. We evaluate AutoSAM on four case studies of increasing complexity: a single-pipe steady-state model, a solid-fuel channel with temperature reactivity feedback, the Advanced Burner Test Reactor core, and the Molten Salt Reactor Experiment primary loop. Across all cases, the agent produces runnable SAM models consistent with expected thermal-hydraulic behavior while explicitly identifying missing data and labeling assumed values. The framework achieves 100% utilization of structured inputs, about 88% extraction from PDF text, and 100% completeness in vision-based geometric extraction. These results demonstrate a practical path toward prompt-driven reactor modeling, in which analysts provide system descriptions and supporting documentation while the agent translates them into transparent, and executable, SAM simulations.

Problem

• input file generation
• thermal-hydraulics codes
• engineering document processing
• reactor system modeling
• data extraction

Innovation

• Retrieval-Augmented Generation
• Multimodal AI
• Automated Input Generation
• Thermal-Hydraulics Simulation
• Agentic Framework