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.
@article{arxiv.2604.06279,
title = {Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations},
author = {Ruichen Zhang and Feda AlMuhisen and Chenguang Wan and Zhisong Qu and Kunpeng Li and Youngwoo Cho and Kyungtak Lim and Virginie Grandgirard and Xavier Garbet},
journal= {arXiv preprint arXiv:2604.06279},
year = {2026}
}