Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Ruichen, AlMuhisen, Feda, Wan, Chenguang, Qu, Zhisong, Li, Kunpeng, Cho, Youngwoo, Lim, Kyungtak, Grandgirard, Virginie, Garbet, Xavier
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917389143113728
author Zhang, Ruichen
AlMuhisen, Feda
Wan, Chenguang
Qu, Zhisong
Li, Kunpeng
Cho, Youngwoo
Lim, Kyungtak
Grandgirard, Virginie
Garbet, Xavier
author_facet Zhang, Ruichen
AlMuhisen, Feda
Wan, Chenguang
Qu, Zhisong
Li, Kunpeng
Cho, Youngwoo
Lim, Kyungtak
Grandgirard, Virginie
Garbet, Xavier
contents Accurate parameter selection is fundamental to gyrokinetic plasma simulations, yet current practices rely heavily on manual literature reviews, leading to inefficiencies and inconsistencies. We introduce Plasma GraphRAG, a novel framework that integrates Graph Retrieval-Augmented Generation (GraphRAG) with large language models (LLMs) for automated, physics-grounded parameter range identification. By constructing a domain-specific knowledge graph from curated plasma literature and enabling structured retrieval over graph-anchored entities and relations, Plasma GraphRAG enables LLMs to generate accurate, context-aware recommendations. Extensive evaluations across five metrics, comprehensiveness, diversity, grounding, hallucination, and empowerment, demonstrate that Plasma GraphRAG outperforms vanilla RAG by over $10\%$ in overall quality and reduces hallucination rates by up to $25\%$. {Beyond enhancing simulation reliability, Plasma GraphRAG offers a methodology for accelerating scientific discovery across complex, data-rich domains.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06279
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations
Zhang, Ruichen
AlMuhisen, Feda
Wan, Chenguang
Qu, Zhisong
Li, Kunpeng
Cho, Youngwoo
Lim, Kyungtak
Grandgirard, Virginie
Garbet, Xavier
Plasma Physics
Artificial Intelligence
Accurate parameter selection is fundamental to gyrokinetic plasma simulations, yet current practices rely heavily on manual literature reviews, leading to inefficiencies and inconsistencies. We introduce Plasma GraphRAG, a novel framework that integrates Graph Retrieval-Augmented Generation (GraphRAG) with large language models (LLMs) for automated, physics-grounded parameter range identification. By constructing a domain-specific knowledge graph from curated plasma literature and enabling structured retrieval over graph-anchored entities and relations, Plasma GraphRAG enables LLMs to generate accurate, context-aware recommendations. Extensive evaluations across five metrics, comprehensiveness, diversity, grounding, hallucination, and empowerment, demonstrate that Plasma GraphRAG outperforms vanilla RAG by over $10\%$ in overall quality and reduces hallucination rates by up to $25\%$. {Beyond enhancing simulation reliability, Plasma GraphRAG offers a methodology for accelerating scientific discovery across complex, data-rich domains.
title Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations
topic Plasma Physics
Artificial Intelligence
url https://arxiv.org/abs/2604.06279