Vals AI · 2026-10-04 · notable
Claude Opus 5.5 agents find two room-temperature magnetic semiconductors
A team of Claude Opus 5.5 agents, working with Geby Jaff, used DFT simulations to propose two magnetic semiconductors for spintronic memory, YBaMnFeO5 and KV[Cr(CN)6]. The inputs, outputs and analysis code are public.
Claude Opus 5.5 agents ran quantum simulations and found two candidate materials for faster, low-interference memory.
What is it?
Writing on the Vals AI blog, Geby Jaff and a team of Claude Opus 5.5 agents report two candidate 'Luttinger compensated' magnetic semiconductors that should work at room temperature. One, YBaMnFeO5, was designed with the agents; the other, KV[Cr(CN)6], was first made in 1999 and was found by the agents in the literature.
How does it work?
The agents ran density functional theory simulations at two levels: a faster PBE+U pass and a slower, usually more accurate HSE06 pass. These materials have zero net magnetism but still sort electrons by spin energy. The predictions put YBaMnFeO5 at a 2.35 eV band gap, magnetic up to about 420 K, and KV[Cr(CN)6] at 2.1 eV, magnetic up to 376 K.
Why does it matter?
Spintronic memory built from such materials could switch about a thousand times faster than ferromagnetic memory and disturb nearby parts less, according to the post. The work is computational only: neither band gap nor spin sorting has been measured, and the next step is to remake KV[Cr(CN)6] and test it.
Who is it for?
materials scientists and anyone tracking AI-for-science agents