AutoMOOSE: AI Chef for New Materials express

Original: "AutoMOOSE: An Agentic AI for Autonomous Phase-Field Simulation"
arXiv:2603.20986 · 2026-03-22 · CC BY 4.0 · 1 min
AutoMOOSE is an open system that, from a plain-language phrase, runs a full cycle of computer modeling of a material.

Creating a new material, like a tough alloy, requires thousands of computer experiments. Usually, a scientist manually writes instructions and hunts for errors. AutoMOOSE is a robotic kitchen: say 'I want a light and strong metal,' and five software chefs whip up a recipe, launch the synthesis, and adjust if something goes wrong.

The system also keeps a detailed lab notebook, like a head chef recording a new recipe so others can replicate it.

In a test on copper grain growth, AutoMOOSE showed accuracy nearly matching an expert, and corrected three typical errors without human help. Grain growth is driven by entropy and determines strength. The approach is universal: from carbon composites to semiconductors, based on the standard model of microstructure.

The five AI agents in AutoMOOSE work like a well-coordinated kitchen brigade: one writes the recipe, another checks the ingredients, a third cooks, a fourth tastes, and a fifth ensures everything stays on track. And all the user needs to do is say a couple of plain-language phrases.

Scientists
Ludwig BoltzmannRudolf ClausiusJacob BekensteinStephen HawkingJames Clerk MaxwellEdward Witten
Concepts
ai self correction agent automated analysis automation voice assistant artificial intelligence ai scientific assistant frame ai drug discovery atp