Agentic framework for programmatic crystal structure generation using a fine-tuned worker–supervisor large language model

Viktoriia Baibakova

doi:10.1016/j.egyai.2026.100710

Agentic framework for programmatic crystal structure generation using a fine-tuned worker–supervisor large language model

2026-03-02

0

OA

AI

V

Viktoriia Baibakova *

A

Alexey Serov

DOI：10.1016/j.egyai.2026.100710

Original

Original request for help

Save

Abstract

En 中文

• Compact AI agentic framework for crystal structure generation: a fine-tuned 350M-parameter worker model (CodeGen) and large supervisor model (Claude) successfully translate natural language into programmatic Pymatgen code, enabling usable crystal structures without billion-scale LLMs. • Energy-efficient and responsible AI: training and inference use orders of magnitude fewer resources than large foundation models, aligning with sustainable AI practices while retaining meaningful crystallographic reasoning. • Programmatic rather than file-based generation: the agent outputs Pymatgen code instead of full CIFs, making results compact, interpretable, and easily verified or manipulated by researchers. • Strong performance gains from fine-tuning: hallucination rates decreased from 100% in the baseline to as low as 5%, with structural match accuracy up to 82% for fully specified prompts. • Flexible handling of prompt abstraction: the model accommodates a spectrum of descriptions, from fully detailed crystallographic parameters to minimal inputs (stoichiometry + space group), demonstrating potential for both experts and non-experts. • Practical utility for catalysis: applied to benchmark noble-metal and earth-abundant catalysts (IrO2, Pb2Ir2O7, Ni2FeO4, Ni3Mo), the agent generated physically consistent structures suitable for iterative refinement. • Built-in structure manipulation capabilities: the agent can perform supercell scaling, strain application, vacancy creation, and substitution operations directly through natural language commands. • Outlook for integration: this work paves the way for multimodal AI agents that couple text-driven generation with simulation, property prediction, and closed-loop experimental design.

Keywords:

AI agent

Large language models

Responsible AI

Crystal structure

Catalysts

Agentic framework for programmatic crystal structure generation using a fine-tuned worker–supervisor large language model

Abstract

Journal

Organization