MatLLMSearch: Crystal Structure Discovery with Evolution-Guided Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916992012779520 |
|---|---|
| author | Gan, Jingru Zhong, Peichen Du, Yuanqi Zhu, Yanqiao Duan, Chenru Wang, Haorui Schwalbe-Koda, Daniel Gomes, Carla P. Persson, Kristin A. Wang, Wei |
| author_facet | Gan, Jingru Zhong, Peichen Du, Yuanqi Zhu, Yanqiao Duan, Chenru Wang, Haorui Schwalbe-Koda, Daniel Gomes, Carla P. Persson, Kristin A. Wang, Wei |
| contents | Crystal structure generation is fundamental to materials science, enabling the discovery of novel materials with desired properties. While existing approaches leverage Large Language Models (LLMs) through extensive fine-tuning on materials databases, we show that pre-trained LLMs can inherently generate novel and stable crystal structures without additional fine-tuning. Our framework employs LLMs as intelligent proposal agents within an evolutionary pipeline that guides them to perform implicit crossover and mutation operations while maintaining chemical validity. We demonstrate that MatLLMSearch achieves a 78.38% metastable rate validated by machine learning interatomic potentials and 31.7% DFT-verified stability, outperforming specialized models such as CrystalTextLLM. Beyond crystal structure generation, we further demonstrate that our framework adapts to diverse materials design tasks, including crystal structure prediction and multi-objective optimization of properties such as deformation energy and bulk modulus, all without fine-tuning. These results establish our framework as a versatile and effective framework for consistent high-quality materials discovery, offering training-free generation of novel stable structures with reduced overhead and broader accessibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20933 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MatLLMSearch: Crystal Structure Discovery with Evolution-Guided Large Language Models Gan, Jingru Zhong, Peichen Du, Yuanqi Zhu, Yanqiao Duan, Chenru Wang, Haorui Schwalbe-Koda, Daniel Gomes, Carla P. Persson, Kristin A. Wang, Wei Materials Science Machine Learning Crystal structure generation is fundamental to materials science, enabling the discovery of novel materials with desired properties. While existing approaches leverage Large Language Models (LLMs) through extensive fine-tuning on materials databases, we show that pre-trained LLMs can inherently generate novel and stable crystal structures without additional fine-tuning. Our framework employs LLMs as intelligent proposal agents within an evolutionary pipeline that guides them to perform implicit crossover and mutation operations while maintaining chemical validity. We demonstrate that MatLLMSearch achieves a 78.38% metastable rate validated by machine learning interatomic potentials and 31.7% DFT-verified stability, outperforming specialized models such as CrystalTextLLM. Beyond crystal structure generation, we further demonstrate that our framework adapts to diverse materials design tasks, including crystal structure prediction and multi-objective optimization of properties such as deformation energy and bulk modulus, all without fine-tuning. These results establish our framework as a versatile and effective framework for consistent high-quality materials discovery, offering training-free generation of novel stable structures with reduced overhead and broader accessibility. |
| title | MatLLMSearch: Crystal Structure Discovery with Evolution-Guided Large Language Models |
| topic | Materials Science Machine Learning |
| url | https://arxiv.org/abs/2502.20933 |