Year: 2026
Type: preprint
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.
Source: arXiv (Cornell University)
Institutions: Nankai University, CIC nanoGUNE
Language: English
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: green
Awards: G1545788684, G3216273683, G6693106366
OpenAlex ID: W7222760228