Using large language models for enhancing accessibility for Monte Carlo photon transport simulations and beyond

Moore’s Law for Molecular Dynamics Simulations: An Initial Study

High-performance computing (HPC) is essential to modern molecular dynamics (MD) simulations. While computing capabilities continue to grow, it remains unclear how these advances translate into everyday scientific practice. Additional resources may be used to reduce time-to-solution, improve model fidelity, simulate larger systems, extend simulated time scales, or increase the number of independent runs. Understanding how users allocate increased computational capability is important for future system design. To investigate how MD usage has evolved over time, we analyzed over 400 publications reporting all-atom MD simulations using a large language model (LLM)-based extraction workflow. Thirty of these publications were manually reviewed to develop and validate an expert-guided extraction rubric. Using this rubric, we evaluated several LLM configurations for extracting system size, simulation duration, and number of independent runs. Extraction quality improved across successive model generations, from GPT-4o to GPT-5 and then to GPT-5.4. Within the GPT-5.4 family, accuracy decreased as model size was reduced from GPT-5.4 to GPT-5.4-mini and then to GPT-5.4-nano. However, increasing reasoning effort from medium to high made GPT-5.4-nano performance comparable to GPT-5.4 while reducing cost by nearly an order of magnitude. Based on this result, GPT-5.4-nano with high reasoning effort was selected for extraction across the full dataset. Our initial analysis suggests that MD system sizes and the number of independent runs have not grown substantially over the last two decades, whereas simulation duration shows a clearer, approximately exponential increase. The fitted trend suggests that maximum MD simulation duration doubled approximately every 2.2 years between 2005 and 2025. These results demonstrate the feasibility of AI-assisted meta-analysis for understanding historical trends in scientific computing workloads.

Simulation Code Generation for Fluid Systems using Large Language Models: Benchmarking Models and Prompting Strategies

This study explores how LLMs can be harnessed to automatically translate a neutral graph representation of fluid system models into executable code for two widely adopted simulation environments: the Python library WNTR and the Modelica Standard Library.

A Comprehensive Review of Large Language Models for Nanophotonics: From Surrogate Modeling to Autonomous Design

Metasurfaces have revolutionized the development of photonic devices by enabling unprecedented precision in light manipulation. However, their design processes are often constrained by computationally expensive simulations and complex high-dimensional design spaces. Although deep learning has accelerated the design process by serving as a surrogate model, it remains constrained by task-specific architectures and lacks universal reasoning capabilities. This review surveys how Large Language Models (LLMs) are adding semantic interfaces, code generation, and tool orchestration to established numerical nanophotonic workflows. We first outline the development from classical neural networks to transformer-based models and their applications in nanophotonic design. We then review the emergence of LLM-related methods in nanophotonics and organize them into two operational modes: surrogate models that treat structure-spectrum mapping as a language task, and agentic systems that have been demonstrated to generate code, orchestrate selected simulation steps, and support closed-loop optimization. Furthermore, to identify future cross-disciplinary opportunities, we briefly explore applications of LLMs in research fields such as materials science and wireless communications. This review concludes by looking ahead to the next generation of multimodal foundation models with physical perception capabilities. In this vision, artificial intelligence is evolving from passive tools into active collaborators, participating in autonomous scientific discovery.

G4DARI: an intuitive graphical interface for Monte Carlo radiation dose calculation using GATE/GEANT4.

GEometry ANd Tracking, version 4 (GEANT4) Dose and Radiation Interaction (G4DARI) is a GEANT4 Application for Tomographic Emission (GATE)/GEANT4 built graphical, Windows-based interface designed to facilitate Monte Carlo dose calculations in computed tomography images of patients, small animals, and phantoms. Developed to remove the programming barrier commonly associated with handling image formats and using GATE and GEANT4 coding, G4DARI integrates Oracle virtual machine (VM) VirtualBox for running the simulation environment and PuTTY for secure communication between the VM and the host system. The interface allows users to perform complete Monte Carlo dose simulations using only mouse interactions, providing a streamlined workflow for clinically relevant simulations, preclinical and research applications, and educational purposes. This manuscript describes the architecture, workflow, and features of G4DARI, from the conversion of Digital Imaging and Communications in Medicine (DICOM) images to dose determination in any region of the digital image. Furthermore, G4DARI is freely available for download, providing users with an accessible platform for running their own dosimetry simulations.

Physics in Medicine & Biology

Integrating Automated Simulation Workflows with 3D Visualization for Virtual Experiments in the Metaverse.

This protocol demonstrates the deployment and use of a locally containerized workflow system that supports the findable, accessible, interoperable, reusable (FAIR) data principles and supports Scalability to high-performance computing (HPC) or cloud resources via Galaxy's Pulsar system.