Research

Paper

AI LLM March 16, 2026

A proof-of-concept for automated AI-driven stellarator coil optimization with in-the-loop finite-element calculations

Authors

Alan A. Kaptanoglu, Pedro F. Gil

Abstract

Finding feasible coils for stellarator fusion devices is a critical challenge of realizing this concept for future power plants. Years of research work can be put into the design of even a single reactor-scale stellarator design. To rapidly speed up and automate the workflow of designing stellarator coils, we have designed an end-to-end ``runner'' for performing stellarator coil optimization. The entirety of pre and post-processing steps have been automated; the user specifies only a few basic input parameters, and final coil solutions are updated on an open-source leaderboard. Two policies are available for performing non-stop automated coil optimizations through a genetic algorithm or a context-aware LLM. Lastly, we construct a novel in-the-loop optimization of Von Mises stresses in the coils, opening up important future capabilities for in-the-loop finite-element calculations.

Metadata

arXiv ID: 2603.15240
Provider: ARXIV
Primary Category: physics.plasm-ph
Published: 2026-03-16
Fetched: 2026-03-17 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.15240v1</id>\n    <title>A proof-of-concept for automated AI-driven stellarator coil optimization with in-the-loop finite-element calculations</title>\n    <updated>2026-03-16T13:12:41Z</updated>\n    <link href='https://arxiv.org/abs/2603.15240v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.15240v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Finding feasible coils for stellarator fusion devices is a critical challenge of realizing this concept for future power plants. Years of research work can be put into the design of even a single reactor-scale stellarator design. To rapidly speed up and automate the workflow of designing stellarator coils, we have designed an end-to-end ``runner'' for performing stellarator coil optimization. The entirety of pre and post-processing steps have been automated; the user specifies only a few basic input parameters, and final coil solutions are updated on an open-source leaderboard. Two policies are available for performing non-stop automated coil optimizations through a genetic algorithm or a context-aware LLM. Lastly, we construct a novel in-the-loop optimization of Von Mises stresses in the coils, opening up important future capabilities for in-the-loop finite-element calculations.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='physics.plasm-ph'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='physics.comp-ph'/>\n    <published>2026-03-16T13:12:41Z</published>\n    <arxiv:primary_category term='physics.plasm-ph'/>\n    <author>\n      <name>Alan A. Kaptanoglu</name>\n    </author>\n    <author>\n      <name>Pedro F. Gil</name>\n    </author>\n  </entry>"
}