Toward AI-Agent-Driven Particle Transport Simulations: Implementation of AI-Assisted Workflows for PHITS
Abstract
Monte Carlo particle transport codes are powerful tools, but their use requires substantial knowledge of input preparation, execution, and result analysis. In this study, we present a code-side strategy for applying existing AI assistants and AI agents to PHITS. Two complementary sets of AI-ready resources were prepared from manuals, lecture materials, sample inputs, utility information, and developer-curated cautions: a bundled knowledge base for retrieval-augmented generation (RAG)-based assistants and a compact agent reference for direct use by AI agents. The knowledge base was loaded into Gemini Notebook to provide conversational PHITS support, while the agent reference was combined with PHITS-specific policies and execution rules to enable AI agents to edit input files, execute calculations, inspect errors, analyze results, and assist with source-code modification and compilation. To evaluate the agent-driven workflow, five demonstration tasks were executed ten times with different AI agents and computing environments. The results showed that AI agents could handle complex PHITS workflows when appropriate resources and rules were provided. Practical lessons included precise prompts, human verification, well-documented sample files, explicit execution policies, and command-line-accessible tools. These findings support bundling AI-ready resources with particle transport codes to enable the use of general-purpose AI tools without requiring dedicated code-specific applications.
Versions
Related
- Analysis of the alpha particle transport induced by Alfven eigenmodes and fish-bones in JET DT discharges: multiple energetic particle simulations
- STORM: RDMA-based Monte Carlo Transport Scheme for Distributed-Memory Particle Simulations
- Lowering the implementation barrier of neutral-atom quantum computing with agentic workflows
- ColPackAgent: Agent-Skill-Guided Hard-Particle Monte Carlo Workflows for Colloidal Packing
- Colour-Field Based Particle Categorization for Residual Stress Detection and Reduction in Solid SPH Simulations
BibTeX
@misc{sato2026toward,
title = {{Toward AI-Agent-Driven Particle Transport Simulations: Implementation of AI-Assisted Workflows for PHITS}},
author = {Tatsuhiko Sato and Shintaro Hashimoto and Tatsuhiko Ogawa and Takuya Furuta and Yuho Hirata and Seiki Ohnishi and Yasuhito Sakaki and Nobuhiro Shigyo},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2607.11309},
eprint = {2607.11309},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.11309},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Toward AI-Agent-Driven Particle Transport Simulations: Implementation of AI-Assisted Workflows for PHITS
AU - Tatsuhiko Sato
AU - Shintaro Hashimoto
AU - Tatsuhiko Ogawa
AU - Takuya Furuta
AU - Yuho Hirata
AU - Seiki Ohnishi
AU - Yasuhito Sakaki
AU - Nobuhiro Shigyo
PY - 2026
DA - 2026/09/30
PB - arXiv
DO - 10.48550/arxiv.2607.11309
UR - https://arxiv.org/abs/2607.11309
AB - Monte Carlo particle transport codes are powerful tools, but their use requires substantial knowledge of input preparation, execution, and result analysis. In this study, we present a code-side strategy for applying existing AI assistants and AI agents to PHITS. Two complementary sets of AI-ready resources were prepared from manuals, lecture materials, sample inputs, utility information, and developer-curated cautions: a bundled knowledge base for retrieval-augmented generation (RAG)-based assistants and a compact agent reference for direct use by AI agents. The knowledge base was loaded into Gemini Notebook to provide conversational PHITS support, while the agent reference was combined with PHITS-specific policies and execution rules to enable AI agents to edit input files, execute calculations, inspect errors, analyze results, and assist with source-code modification and compilation. To evaluate the agent-driven workflow, five demonstration tasks were executed ten times with different AI agents and computing environments. The results showed that AI agents could handle complex PHITS workflows when appropriate resources and rules were provided. Practical lessons included precise prompts, human verification, well-documented sample files, explicit execution policies, and command-line-accessible tools. These findings support bundling AI-ready resources with particle transport codes to enable the use of general-purpose AI tools without requiring dedicated code-specific applications.
ER -