Reasoning-Driven Design of Single-Atom Catalysts via a Multiagent Large Language Model Framework
Dong Hyeon Mok, Seoin Back, Victor Fung, Guoxiang Hu · 2026
Read Reasoning-Driven Design of Single-Atom Catalysts via a Multiagent Large Language Model Framework by Dong Hyeon Mok, Seoin Back, Victor Fung, Guoxiang Hu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13614041.txt.
Description
Single atoms of metal pinned on a support can drive clean fuel-cell chemistry, and finding the best atom-and-support pairs by lab trial is slow. Dong Hyeon Mok and co-authors let a team of language models do the hunting in a 2026 paper. Each model plays a role: proposing designs, judging results, and remembering what worked, in a loop that runs on its own.
Across rounds the agents reasoned their way to design rules that were not handed to them. The loop found catalysts that break a standard trade-off between the steps of the oxygen reaction, a wall that has long capped this class. The authors present the system as a new kind of lab partner, one that builds chemical insight while it searches, not just a faster sieve for candidates.
Catalog record
| CREATOR | Dong Hyeon Mok, Seoin Back, Victor Fung, Guoxiang Hu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |