The overarching goal of the proposed project directly addresses the arpa-e magnito program objective: to discover, synthesize, and validate new, ultra-performing permanent magnets with performance…

The Department of Energy Advanced Research Projects Agency awarded a $2.295 million cooperative agreement to the Massachusetts Institute of Technology on July 30, 2026, under the Advanced Research Projects Agency–Energy program (CFDA 81.135) to discover, synthesize, and validate new ultra-performing permanent magnets with performance beyond neodymium-iron-boron (Nd-Fe-B) magnet formulations while ensuring manufacturability, scalability, and cost competitiveness.

MIT will establish a property-first, physics-informed closed-loop artificial intelligence–experiment system that integrates generative modeling, alloy and defect-sensitive representations, ab initio and micromagnetic simulations, and direct experimental feedback. This platform addresses the ARPA-E MAGNITO program objective to reduce U.S. reliance on critical rare-earth elements and accelerate domestic leadership in next-generation magnet technology.

Work is performed in Cambridge, Massachusetts. The period of performance runs from July 30, 2026, through July 29, 2029.

The overarching goal of the proposed project directly addresses the arpa-e magnito program objective: to discover, synthesize, and validate new, ultra-performing permanent magnets with performance beyond ND-FE-b magnet like ND2FE14B while ensuring manufacturability, scalability, and cost competitiveness. Our approach establishes a property-first, physics-informed, closedloop AI-experiment system that unites generative modeling, alloy and defect-sensitive representations, AB-initio and micromagnetic simulations, and direct experimental feedback. This platform advances arpa-ES mission to reduce reliance on critical rare-earths and accelerate U.S. Leadership in next-generation magnet technology.