Metraipolis › archive › dc_bb7ceea9dde6

Crystal-structure design by agentic AI in a language of motifs — arXiv:2608.15900

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.15900
License (as archived): CC0-1.0
Archived: 2026-10-18T19:44:16.553Z
SHA-256 of the archived text: 0a4140377e17f6213c35e2f9eb694843651fc0a558fca495eecb4765653bc634
Stable URL of this page: https://metraipolis.com/documento/dc_bb7ceea9dde6

How to cite

Crystal-structure design by agentic AI in a language of motifs — arXiv:2608.15900 — arXiv (en), https://arxiv.org/abs/2608.15900 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb7ceea9dde6 (Metraipolis archive dc_bb7ceea9dde6, sha256 0a4140377e17f6213c35e2f9eb694843651fc0a558fca495eecb4765653bc634)

BibTeX

@misc{dcbb7ceea9dde6,
  title = {Crystal-structure design by agentic AI in a language of motifs — arXiv:2608.15900},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15900},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb7ceea9dde6; sha256 0a4140377e17f6213c35e2f9eb694843651fc0a558fca495eecb4765653bc634},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15900. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Data-driven materials discovery interpolates more reliably than it extrapolates and seldom reaches new structure types. We present MatEvolve, an agentic-AI framework designing crystals, proposing each candidate with a stated rationale and testing it. The agent reasons in an interpretable \emph{language of motifs}, writing each crystal as a \emph{motif profile} that describes the recurring geometric patterns---the \emph{motifs}---composing it. The motif profile serves not merely as a description of a material but as the medium for material design: the agent edits the profile and constructs a crystal from the modified one, and the most promising candidates are validated by first-principles calculation. Applied to the design of rare-earth-lean permanent magnets, MatEvolve---built on the state-of-the-art language model Claude Fable~5 without fine-tuning---reaches new structural prototypes more than three times as often as generative models under an equal validation budget, at a comparable on-target-magnet rate. Beyond design, analysing the discovered crystals' human-readable profiles reveals structure--property relationships.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Materials Science (cond-mat.mtrl-sci) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.15900 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T19:02:44.286Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).