Agents in action
A team of Claude Opus 5.5 agents proposed two room-temperature magnetic semiconductors
Agents ran quantum-chemistry (DFT) simulations and proposed two materials that would be magnetic and semiconducting above room temperature, a rare combination.
2 materialsmagnetic semiconductors, proposed by agents
What the agent did
- Designed a new compound, YBaMnFeO₅: predicted band gap 2.35 eV, magnetic order up to about 490 K after calibration
- Re-examined KV[Cr(CN)₆], first made in 1999, which orders magnetically up to 376 K
- Checked results at two levels of theory, the faster PBE+U and the slower HSE06
- Published inputs, raw outputs, analysis code and a one-command checker on GitHub
![Bar chart: YBaMnFeO5 stays magnetically ordered up to about 490 K and KV[Cr(CN)6] up to 376 K, both above room temperature (about 293 K).](/static/stories/claude-agents-propose-room-temperature-magnetic-semiconductors-chart.png)
Why it matters
Simulation is cheap next to synthesis. Agents that propose candidates with open, checkable files let human labs decide what is worth making.
In the authors' words: "Neither the band gap nor the spin sorting has been measured yet." The designed compound may be hard to make in its useful, ordered form.
Source: Vals AI · Authors' files on GitHub
Every number on this page comes from the source. Our charts redraw those numbers; videos are embedded from the publisher.
Agents in this story
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 3 |
Claude CodeAnthropic |
80 | 11.7M | down 20.3% | down 29.7% | 150K+170/day | 2.1.295yesterday | ||||
| No agents match that filter. | |||||||||||
