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

arXiv: https://arxiv.org/abs/2603.24736 · HTML: https://mlsanity.com/paper/2603.24736/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 13 of its 45 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Placed in

- Retrieval-augmented generation / [RAG for code](https://mlsanity.com/rag/rag-for-code/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 13 of 13)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [Retrieval meets Long Context Large Language Models](https://mlsanity.com/paper/2310.03025/) (2023)
- [BioRAG: A RAG-LLM Framework for Biological Question Reasoning](https://mlsanity.com/paper/2408.01107/) (2024)
- [BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model](https://mlsanity.com/paper/2505.23579/) (2025)
- [CLLMate: A Multimodal Benchmark for Weather and Climate Events Forecasting](https://mlsanity.com/paper/2409.19058/) (2024)
- [MatterChat: A Multi-Modal LLM for Material Science](https://mlsanity.com/paper/2502.13107/) (2025)
- [Effects of Prompt Length on Domain-specific Tasks for Large Language Models](https://mlsanity.com/paper/2502.14255/) (2025)
- [A Multi-LLM-Agent-Based Framework for Economic and Public Policy Analysis](https://mlsanity.com/paper/2502.16879/) (2025)
- [Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics](https://mlsanity.com/paper/2510.09901/) (2025)
- [An AI-Driven Thermal-Fluid Testbed for Advanced Small Modular Reactors: Integration of Digital Twin and Large Language Models](https://mlsanity.com/paper/2507.06399/) (2025)
- [TRIZ-GPT: An LLM-augmented method for problem-solving](https://mlsanity.com/paper/2408.05897/) (2024)
- [Automating Data-Driven Modeling and Analysis for Engineering Applications using Large Language Model Agents](https://mlsanity.com/paper/2510.01398/) (2025)

## Built on by (most cited first, 2 of 2)

- [Graph Neural ODE Digital Twins for Control-Oriented Reactor Thermal-Hydraulic Forecasting Under Partial Observability](https://mlsanity.com/paper/2604.07292/) (2026)
- [PHITSBench: an execution-scored benchmark for AI-assisted PHITS radiation-transport input generation using natural language](https://mlsanity.com/paper/2607.09789/) (2026)

## Abstract (arXiv)

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.