AI Market Logo
BTC $43,552.88 -0.46%
ETH $2,637.32 +1.23%
BNB $312.45 +0.87%
SOL $92.40 +1.16%
XRP $0.5234 -0.32%
ADA $0.8004 +3.54%
AVAX $32.11 +1.93%
DOT $19.37 -1.45%
MATIC $0.8923 +2.67%
LINK $14.56 +0.94%
HAIA $0.1250 +2.15%
BTC $43,552.88 -0.46%
ETH $2,637.32 +1.23%
BNB $312.45 +0.87%
SOL $92.40 +1.16%
XRP $0.5234 -0.32%
ADA $0.8004 +3.54%
AVAX $32.11 +1.93%
DOT $19.37 -1.45%
MATIC $0.8923 +2.67%
LINK $14.56 +0.94%
HAIA $0.1250 +2.15%
LLNL deploys AI agents for fusion target design on supercomputers
supercomputing

LLNL deploys AI agents for fusion target design on supercomputers

LLNL's MADA system uses AI agents on El Capitan supercomputer to automate and accelerate inertial confinement fusion target design.

August 5, 2025
5 min read
Brian Buntz

LLNL's MADA system uses AI agents on El Capitan supercomputer to automate and accelerate inertial confinement fusion target design.

LLNL Deploys AI Agents for Fusion Target Design on Supercomputers

Lawrence Livermore National Laboratory (LLNL) has deployed the Multi-Agent Design Assistant (MADA) to accelerate inertial confinement fusion (ICF) target design. This innovative system integrates large language models (LLMs) with LLNL’s 3D multiphysics simulation code, MARBL, aiming to automate the generation of complex simulation decks. Researchers run MADA on the El Capitan supercomputer, one of the fastest globally with a peak performance of 2.79 exaFLOPs, and its smaller counterpart, Tuolumne. The system employs two AI agents working together: an "Inverse Design Agent" that converts hand-drawn capsule diagrams into thousands of simulation scenarios, and a "Job Management Agent" that schedules and manages these simulations across high-performance computing (HPC) resources. The project, which began development in 2019, was led by LLNL physicist Jon Belof. Initially, the team explored combining AI with shockwave physics—a concept once considered unconventional. In a recent demonstration, an open-source LLM fine-tuned on MARBL documentation successfully interpreted a hand-drawn capsule design and a natural language request from a human designer, then generated a complete simulation deck and executed thousands of simulations exploring variations in ICF capsule geometry. Belof emphasizes that AI agents can drastically compress design cycles, enabling researchers to explore hundreds or thousands of design concepts in parallel instead of just a few.
"Rather than the human running ensembles of simulations, they will be able to run ensembles of ideas." — Jon Belof
Following LLNL’s December 2022 ignition milestone, the laboratory is now focused on developing a robust high-gain fusion platform for national security applications.

Two Agents Working in Concert

The MADA framework is composed of two primary AI agents:
  • Inverse Design Agent: Responsible for generating design concepts by translating hand-drawn diagrams into simulation inputs.
  • Job Management Agent: Oversees the execution of large-scale simulation workflows, coordinating with the Flux scheduler and workflow tools like Merlin.
  • Giselle Fernandez, the Job Management Agent Team Lead, explains, "The Job Management Agent brings AI and HPC together to coordinate agents that handle resource management and workflow optimization at massive scales." The team has already achieved promising results by running tens of thousands of ICF simulations on the Tuolumne supercomputer. The simulation outputs train a machine learning model called PROFESSOR, which provides instant feedback to designers. According to Belof, "Once trained, the PROFESSOR model generates implosion time histories—radius as a function of time—that change instantaneously when the human designer modifies the input geometry." Funding for MADA comes from the National Nuclear Security Administration’s Advanced Simulation & Computing program. The project team includes LLNL researchers Charles Jekel, Rob Rieben, Will Schill, Meir Shachar, and Dane Sterbentz, along with collaborators Nathan Brown from Sandia National Laboratories and Ismael Djibrilla Boureima from Los Alamos National Laboratory. Belof highlights the novelty of the system: "We are putting AI in the driver’s seat of a supercomputer, which is something that has never been done before."

    Federal Agencies Test Agentic AI—With Mixed Results

    LLNL’s advancements come amid broader government experimentation with agentic AI systems. In June 2025, the FDA introduced "Elsa," an AI assistant trained on Anthropic’s Claude. Elsa has received mixed feedback; some staff report it helps parse test reports and reduces review times, while others note its knowledge cutoff in April 2024 and occasional outdated responses. Elsa carries a disclaimer advising users to verify its answers due to potential mistakes. Meanwhile, NASA’s Goddard Space Flight Center is developing "text to structures" and "text to spaceship" projects, enabling scientists to describe spacecraft designs in natural language and receive AI-generated lightweight, efficient structures. Omar Hatamleh, Goddard’s chief AI officer, notes experimentation with agentic workflows to streamline procurement and finance by automating routine tasks. A January 2025 Nextgov/FCW column predicted AI agents would automate back-office tasks and optimize workflows in government, freeing staff for higher-value work. It highlighted the U.S. Patent and Trademark Office’s AI-assisted search system as a successful example of AI improving efficiency and accuracy.

    Industry Hype Meets Organizational Reality

    Consulting firms are promoting agentic AI’s economic potential. Capgemini’s July 2025 report estimates up to $450 billion in revenue growth and cost savings by 2028. However, only 2% of organizations have deployed AI agents at scale, and trust in fully autonomous agents dropped from 43% to 27% in one year. The report stresses the need to redesign processes, rethink business models, and balance autonomy with human oversight. Similarly, McKinsey’s January 2025 report "Superagency" describes agentic AI’s current ability to autonomously handle customer interactions, payments, and fraud checks. Despite software vendors embedding agentic features into platforms to create "digital workforces," only 1% of companies consider themselves mature in AI deployment.
    Originally published at Research & Development World on August 4, 2025.

    Frequently Asked Questions (FAQ)

    LLNL's AI Deployment for Fusion Target Design

    Q: What is the Multi-Agent Design Assistant (MADA) system? A: MADA is an innovative system developed by Lawrence Livermore National Laboratory (LLNL) that integrates Large Language Models (LLMs) with LLNL's simulation code, MARBL, to automate the design of inertial confinement fusion (ICF) targets. Q: How does MADA utilize AI agents? A: MADA employs two primary AI agents: an "Inverse Design Agent" that converts design diagrams into simulation scenarios, and a "Job Management Agent" that schedules and manages these simulations on supercomputers. Q: On which supercomputers is MADA deployed? A: MADA is deployed on LLNL's El Capitan supercomputer and its counterpart, Tuolumne. Q: What is the main benefit of using MADA for fusion target design? A: MADA can drastically compress design cycles, allowing researchers to explore significantly more design concepts in parallel, moving from a few ideas to hundreds or thousands. Q: What is the goal of LLNL's current fusion research after the ignition milestone? A: LLNL is focused on developing a robust high-gain fusion platform for national security applications. Q: What is the role of the PROFESSOR model in the MADA framework? A: The PROFESSOR model is trained on simulation outputs from MADA and provides instant feedback to designers on how geometry changes affect implosion time histories. Q: What is unique about LLNL's approach with MADA? A: LLNL is described as putting AI in the driver's seat of a supercomputer, a novel approach to utilizing AI in scientific simulation.

    AI in Government Operations

    Q: Are other federal agencies experimenting with agentic AI? A: Yes, agencies like the FDA and NASA are experimenting with agentic AI. The FDA has an AI assistant named Elsa, and NASA is developing "text to structures" and "text to spaceship" projects. Q: What have been the results of government AI agent testing? A: Results have been mixed. While some AI assistants have improved efficiency, others have shown limitations like knowledge cutoffs and occasional outdated responses. Q: What are the predicted benefits of AI agents in government? A: AI agents are predicted to automate back-office tasks and optimize workflows, freeing up staff for more complex work.

    Industry Trends in AI Agents

    Q: What is the economic potential of agentic AI according to consulting firms? A: Consulting firms like Capgemini estimate significant revenue growth and cost savings, potentially up to $450 billion by 2028. Q: What is the current state of AI agent deployment in organizations? A: Despite the hype, only a small percentage of organizations have deployed AI agents at scale, and trust in fully autonomous agents has declined. Q: What are the key challenges for organizations adopting AI agents? A: Key challenges include the need to redesign processes, rethink business models, and strike a balance between agent autonomy and human oversight.

    Crypto Market AI's Take

    The deployment of AI agents like MADA at LLNL showcases the transformative power of artificial intelligence in accelerating complex scientific research and development. This mirrors the advancements we're seeing in the financial sector, where AI is revolutionizing market analysis and trading strategies. At Crypto Market AI, we leverage advanced AI and machine learning models to provide our users with cutting-edge AI-powered crypto trading bots and insightful market analysis. Our platform aims to democratize sophisticated trading techniques, making them accessible to a wider audience, much like how LLNL is pushing the boundaries of scientific discovery with AI. Understanding these applications of AI across different domains highlights the growing importance of AI-driven tools for efficiency and innovation.

    More to Read:

  • AI Agents Capabilities, Risks, and Growing Role
  • AI-Driven Crypto Trading Tools Reshape Market Strategies
  • The Future of Cryptocurrency Explained