Skip to content
DraconiticResearch
Search Sources API
197,785 studies31 sourcesUpdated 50 min ago
PreprintCC BY 4.0arXiv

MASON: Materials Atomistic Structure builder Operated in Natural language

  • Xinyue Zhang
  • Jixiang Li
  • Bin Shao
  • Baishun Yang
  • Zhiyang Liu
  • Weichao Wang
Open at sourcePDFDOICite

Abstract

Building reliable atomistic models is a critical and often challenging step in first-principles calculations. Although large language model agents can assist with structure generation, they lack direct capabilities for crystallographic operations and therefore struggle to construct complex structures reliably. Here we present MASON, an AI-native toolkit for atomistic structure construction that can be invoked by agents through the Model Context Protocol (MCP). In an end-to-end example, an agent builds a CO/Pt(111) adsorption model from a natural language request. By equipping agents with dedicated structure-building tools, MASON enables reliable and efficient atomistic model construction and provides a foundation for autonomous first-principles workflows.

Related

  1. Atomistic Modeling of Chemical Disorder in Materials: Bridging Conventional Methods and AI-Assisted Approaches
    Jiayu Peng, Peichen Zhong
    arXivPreprintCC BY 4.0Full textPhysical chemistryCondensed matterarXiv
  2. Atomistic prediction of magnetic behaviour across chemistry, structure and temperature
    Ruosong Shi, Chengbing Chen, Bicheng Liu +15
    arXivPreprintCC BY 4.0Full textCondensed matterarXiv
  3. Atomistic Insights into the Hydration Structure of Stachyose: A Minimum-Distance Distribution Function Approach
    Xiankai Jiang, Yuqiao Shen, Xiaolei Yin +2
    MoleculesPeer-reviewedCC BY 4.0Atomic, molecular & optical physicsCrossref
  4. Automated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models
    Aravindan Kamatchi Sundaram, B. Pabitramohan Prusty, Rohit Batra
    arXivPreprintarXiv licenceFull textCondensed matterarXiv
  5. Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model
    Markus J. Buehler
    arXivPreprintCC BY-NC-ND 4.0Full textCondensed matterarXiv

Cite

BibTeXRIS
BibTeX
@misc{zhang2026mason,
  title = {{MASON: Materials Atomistic Structure builder Operated in Natural language}},
  author = {Xinyue Zhang and Jixiang Li and Bin Shao and Baishun Yang and Zhiyang Liu and Weichao Wang},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.21015},
  eprint = {2610.21015},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.21015},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - MASON: Materials Atomistic Structure builder Operated in Natural language
AU  - Xinyue Zhang
AU  - Jixiang Li
AU  - Bin Shao
AU  - Baishun Yang
AU  - Zhiyang Liu
AU  - Weichao Wang
PY  - 2026
DA  - 2026/10/14
PB  - arXiv
DO  - 10.48550/arxiv.2610.21015
UR  - https://arxiv.org/abs/2610.21015
AB  - Building reliable atomistic models is a critical and often challenging step in first-principles calculations. Although large language model agents can assist with structure generation, they lack direct capabilities for crystallographic operations and therefore struggle to construct complex structures reliably. Here we present MASON, an AI-native toolkit for atomistic structure construction that can be invoked by agents through the Model Context Protocol (MCP). In an end-to-end example, an agent builds a CO/Pt(111) adsorption model from a natural language request. By equipping agents with dedicated structure-building tools, MASON enables reliable and efficient atomistic model construction and provides a foundation for autonomous first-principles workflows.
ER  -