Multi-Agent Collaboration for Automated Design Exploration on High Performance Computing Systems

2026-03-12

AI Summary

This work addresses the challenges of high-dimensional design spaces and inefficient manual workflows in scientific design exploration, such as suppressing Richtmyer–Meshkov instabilities in inertial confinement fusion. The authors propose MADA, a multi-agent framework that, for the first time, integrates large language model–driven collaborative agents into scientific computing. MADA orchestrates specialized agents for task management, geometry generation, and inverse design, enabling seamless integration of simulation, reasoning, and tool invocation on high-performance computing (HPC) platforms. This approach establishes a reusable, automated scientific workflow that autonomously performs iterative optimization for Richtmyer–Meshkov instability suppression, drastically reducing human intervention while supporting both full-fidelity HPC simulations and surrogate models to efficiently approximate optimal designs.

Technology Category

• Multiagent Systems: Teamwork
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Today's scientific challenges, from climate modeling to Inertial Confinement Fusion design to novel material design, require exploring huge design spaces. In order to enable high-impact scientific discovery, we need to scale up our ability to test hypotheses, generate results, and learn from them rapidly. We present MADA (Multi-Agent Design Assistant), a Large Language Model (LLM) powered multi-agent framework that coordinates specialized agents for complex design workflows. A Job Management Agent (JMA) launches and manages ensemble simulations on HPC systems, a Geometry Agent (GA) generates meshes, and an Inverse Design Agent (IDA) proposes new designs informed by simulation outcomes. While general purpose, we focus development and validation on Richtmyer--Meshkov Instability (RMI) suppression, a critical challenge in Inertial Confinement Fusion. We evaluate on two complementary settings: running a hydrodynamics simulations on HPC systems, and using a pre-trained machine learning surrogate for rapid design exploration. Our results demonstrate that the MADA system successfully executes iterative design refinement, automatically improving designs toward optimal RMI suppression with minimal manual intervention. Our framework reduces cumbersome manual workflow setup, and enables automated design exploration at scale. More broadly, it demonstrates a reusable pattern for coupling reasoning, simulation, specialized tools, and coordinated workflows to accelerate scientific discovery.

Problem

• design exploration
• high performance computing
• multi-agent collaboration
• Richtmyer-Meshkov Instability
• automated design

Innovation

• Multi-Agent System
• Large Language Model (LLM)
• High Performance Computing (HPC)
• Automated Design Exploration
• Inverse Design