LLNL Advances Fusion Target Design Using AI on Exascale Supercomputers

Lawrence Livermore National Laboratory (LLNL) researchers have reached a significant milestone by integrating artificial intelligence (AI) with fusion target design. They deployed AI agents on two of the world’s most powerful supercomputers to automate and accelerate inertial confinement fusion (ICF) experiments. Part of an AI framework called the Multi-Agent Design Assistant (MADA), LLNL scientists and collaborators combine Large Language Models (LLMs) with advanced simulation tools. This integration allows the interpretation of natural language prompts from human designers and generates complete physics simulation decks for LLNL’s next-generation 3D multiphysics code, MARBL. MARBL excels at designing and analyzing mission-critical, high-energy-density experiments, including ICF. In ICF experiments at LLNL’s National Ignition Facility (NIF), fusion energy is produced when 192 laser beams converge on a tiny target containing deuterium and tritium, triggering a fusion chain reaction. The MADA team uses the exascale El Capitan supercomputer—the world’s fastest at 2.79 exaFLOPs peak—and its smaller sibling Tuolumne to test the AI system. The framework includes an Inverse Design Agent (IDA) responsible for engineering new ICF targets. Jon Belof, a physicist and principal investigator at LLNL, traces the project’s origins to 2019. “At the time, we were really interested in what happens if you combine AI with shockwave physics. It was kind of a strange idea—at least a lot of people thought it was,” Belof said. “Interestingly enough, that wound up being the simple part. As large language models have advanced, the notion of having semi-autonomous AI systems working alongside humans for ICF design seemed like a natural next step.” As AI capabilities rapidly improved, the MADA team—including collaborators from the National Nuclear Security Administration (NNSA) Tri-Labs at Los Alamos (LANL) and Sandia National Laboratories (SNL)—transformed that “strange idea” into a sophisticated AI-driven design workflow that is producing results. In a recent demonstration, an open-source LLM fine-tuned on internal MARBL documentation successfully interpreted a hand-drawn capsule diagram and a natural language request from a human designer. It then generated a complete simulation deck and ran thousands of simulations exploring variations in ICF capsule geometry, resulting in a novel target design. This AI-driven design paradigm arrives at a critical time for fusion research. Following LLNL’s historic ignition achievement at NIF in December 2022, the laboratory aims to develop a robust ignition platform that could unlock new national security applications. Belof emphasized that tools like MADA drastically compress design cycles and explore vast design spaces, helping identify optimal conditions for scaling fusion yields. “By pairing human insight with AI-driven exploration, LLNL hopes to navigate the complex physics of high-gain implosions faster and more efficiently than ever before,” he said. “In principle, AI agents offer a way for us to pursue not just 3-4 distinct ICF design concepts at once—but hundreds or possibly thousands,” Belof explained. “Rather than humans running ensembles of simulations, they will be able to run ensembles of ideas. This concept could be massively transformative.” At the core of MADA are AI "agents"—autonomous software entities composed of two key components: an LLM that understands and responds to human language, and a specialized tooling interface—an executable function enabling the agent to perform domain-specific tasks. For MADA, this tooling generates structured simulation input files and launches them on high-performance computing (HPC) systems. “We are putting AI in the driver’s seat of a supercomputer, which is something that has never been done before,” Belof said. Supporting the Inverse Design Agent is the Job Management Agent (JMA), which manages the execution of large-scale simulation workflows across LLNL's supercomputers. It interacts with the Flux scheduler and workflow management tools like Merlin. The JMA ensures jobs are queued properly, resources allocated efficiently, and simulation outputs harvested for downstream analysis. Together, these agents form a seamless loop between AI planning and HPC execution: the IDA proposes simulation strategies, and the JMA manages the execution pipeline. "The Job Management Agent brings AI and HPC together to coordinate agents that handle resource management and workflow optimization at massive scales, giving us a critical advantage as we push toward a robust ignition platform for fusion energy," said JMA Team Lead Giselle Fernandez. This iterative workflow enables unprecedented interactivity between designers and simulations. Instead of manually coding and launching individual jobs—a process that could take days or weeks—researchers can now explore thousands of design variations in parallel simply by conversing with an AI agent. “The agent can take a capsule diagram and a plain-language prompt like, ‘Explore the effect of changing a certain part of the geometry and translate that into a valid simulation deck for MARBL,’” Belof explained. “It then runs that deck, collects results, and can even build a training dataset to power a surrogate model.” MADA leverages HPC to run massive ensembles—typically tens of thousands of ICF simulations in a single study—across LLNL’s Tuolumne, the world’s 12th fastest supercomputer. The simulation outputs train a machine learning model called PROFESSOR, which provides instant feedback for designers exploring new capsule geometries. “Once trained, the PROFESSOR model generates implosion time histories—radius as a function of time—that change instantaneously when the human designer changes the input geometry,” Belof said. “It’s a powerful new tool for ICF designers made possible by AI, machine learning, and HPC.” By enabling natural language interaction, image interpretation, and rapid simulation-to-model pipelines, the MADA project demonstrates how AI can be embedded directly into high-stakes scientific workflows. This marks a new stage of national security design work—replacing slow, manual iteration with collaborative AI augmentation. The implications extend far beyond ICF. As more exascale-class systems like El Capitan come online, MADA offers a blueprint for AI agents acting as digital collaborators in domains ranging from materials discovery to weapons certification. “It’s really about enhancing human productivity through AI, in a transformative way,” Belof said. “This project shows we’re just beginning to tap what’s possible. AI tools have the potential to help us best allocate resources and understand tradeoffs needed for the next generation of enhanced fusion facilities.” The work is funded by NNSA’s Advanced Simulation & Computing program. Other LLNL MADA team members include deputy principal investigator Charles Jekel, MARBL Project Lead Rob Rieben, and researchers Will Schill, Meir Shachar, and Dane Sterbentz. Nathan Brown of SNL and Ismael Djibrilla Boureima of LANL also contributed.

---

Source: LLNL Pushes Frontier of Fusion Target Design with AI (Lawrence Livermore National Laboratory, August 4, 2025)

Frequently Asked Questions (FAQ)

AI in Scientific Research

Q: How is AI being used to advance fusion target design at LLNL? A: LLNL researchers are using AI agents within a framework called the Multi-Agent Design Assistant (MADA) to automate and accelerate the design and analysis of inertial confinement fusion (ICF) targets. Q: What are the key components of the MADA framework? A: MADA combines Large Language Models (LLMs) with advanced simulation tools, allowing AI agents to interpret natural language prompts and generate physics simulation decks for complex codes like MARBL. Q: What is the role of exascale supercomputers in this project? A: Exascale supercomputers, such as El Capitan and Tuolumne, are used to test and run the AI system, enabling the exploration of vast design spaces and the execution of thousands of simulations. Q: How does the AI system help in designing new fusion targets? A: AI agents, like the Inverse Design Agent (IDA), can interpret hand-drawn diagrams and natural language requests to generate simulation inputs, explore variations, and discover novel target designs much faster than traditional methods. Q: What are the broader implications of this AI-driven design approach? A: This approach can drastically compress design cycles, explore vast design spaces, and potentially lead to the discovery of hundreds or thousands of design concepts, transforming scientific workflows beyond fusion research into areas like materials discovery.

Crypto Market AI's Take

The advancements in AI for scientific research, as demonstrated by LLNL's fusion target design, highlight the growing power and versatility of artificial intelligence. At Crypto Market AI, we are also leveraging AI to revolutionize financial markets. Our platform utilizes AI agents for sophisticated market analysis, automated trading strategies, and personalized financial planning. This fusion of AI and complex problem-solving, whether in fusion energy or financial markets, points towards a future where intelligent systems significantly enhance human capabilities and accelerate discovery and innovation. We believe that AI agents, much like those used at LLNL, can unlock new efficiencies and insights in the dynamic world of cryptocurrency.

More to Read:

• AI Agents: Capabilities, Risks, and Growing Role
• AI-Driven Crypto Trading Tools Reshape Market Strategies