Metraipolis › archive › dc_2543fcbc251e

A self-learning scientific agent for X-ray diffraction — arXiv:2610.07862

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07862
License (as archived)
CC0-1.0
Archived
2026-10-07T11:21:15.565Z
SHA-256 of the archived text
14bb4d757771221d386999a72fc418b384d6153f1520256fae4214ec2e543c2e
Stable URL of this page
https://metraipolis.com/documento/dc_2543fcbc251e

How to cite

A self-learning scientific agent for X-ray diffraction — arXiv:2610.07862 — arXiv (en), https://arxiv.org/abs/2610.07862 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2543fcbc251e (Metraipolis archive dc_2543fcbc251e, sha256 14bb4d757771221d386999a72fc418b384d6153f1520256fae4214ec2e543c2e)
BibTeX
@misc{dc2543fcbc251e,
  title = {A self-learning scientific agent for X-ray diffraction — arXiv:2610.07862},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07862},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2543fcbc251e; sha256 14bb4d757771221d386999a72fc418b384d6153f1520256fae4214ec2e543c2e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07862. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A central challenge for scientific agents is to turn analytical experience into reusable expertise grounded in physical evidence. Here we introduce Gan Jiang, a self-learning agent for powder X-ray diffraction built on a diffraction-analysis ecosystem we developed: XMatcher, XQueryer, XDecomposer and WPEM. Together, these engines span phase identification, multiphase decomposition and physics-constrained whole-pattern modelling. Gan Jiang converts analytical experience into executable skills by diagnosing failures, revising skill instructions and code, and validating revisions before reuse, without retraining the language model or changing the underlying physical models. Skills selected using development data and frozen before held-out evaluation achieve higher refinement scores than the original expert-designed skills across FullProf, GSAS-II and PyWPEM. The agent resolves strongly overlapping reflections, quantifies a five-phase ancient Egyptian cosmetic, tracks lattice evolution in an operating battery and compares atomic configurations in a disordered oxide catalyst. On DeltaXRDbench, it leads the evaluated methods in single- and multiphase identification across simulated and experimental data. Without supplied composition, single-phase top-1 accuracies reach 96.30\%, 81.78\% and 40.83\% on MP500, RRUFF and opXRD, respectively, compared with 58.00\%, 58.47\% and 26.45\% for the strongest comparator. These results demonstrate how an integrated scientific tool ecosystem can support agents that extract structural knowledge from measurements while accumulating validated analytical expertise that transfers to new samples.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Materials Science (cond-mat.mtrl-sci) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.07862 — 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 2026-10-07T11:15:24.774Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).