Saved in:
Bibliographic Details
Main Authors: Yang, Yaotian, Tang, Yiwen, Chen, Yizhe, Chen, Xiao, Qiu, Jiangjie, Xiong, Hao, Yin, Haoyu, Luo, Zhiyao, Zhang, Yifei, Tao, Sijia, Li, Wentao, Zhang, Qinghua, Li, Yuqiang, Ouyang, Wanli, Zhao, Bin, Wang, Xiaonan, Wei, Fei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.12650
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910951866892288
author Yang, Yaotian
Tang, Yiwen
Chen, Yizhe
Chen, Xiao
Qiu, Jiangjie
Xiong, Hao
Yin, Haoyu
Luo, Zhiyao
Zhang, Yifei
Tao, Sijia
Li, Wentao
Zhang, Qinghua
Li, Yuqiang
Ouyang, Wanli
Zhao, Bin
Wang, Xiaonan
Wei, Fei
author_facet Yang, Yaotian
Tang, Yiwen
Chen, Yizhe
Chen, Xiao
Qiu, Jiangjie
Xiong, Hao
Yin, Haoyu
Luo, Zhiyao
Zhang, Yifei
Tao, Sijia
Li, Wentao
Zhang, Qinghua
Li, Yuqiang
Ouyang, Wanli
Zhao, Bin
Wang, Xiaonan
Wei, Fei
contents Machine learning-based interatomic potentials and force fields depend critically on accurate atomic structures, yet such data are scarce due to the limited availability of experimentally resolved crystals. Although atomic-resolution electron microscopy offers a potential source of structural data, converting these images into simulation-ready formats remains labor-intensive and error-prone, creating a bottleneck for model training and validation. We introduce AutoMat, an end-to-end, agent-assisted pipeline that automatically transforms scanning transmission electron microscopy (STEM) images into atomic crystal structures and predicts their physical properties. AutoMat combines pattern-adaptive denoising, physics-guided template retrieval, symmetry-aware atomic reconstruction, fast relaxation and property prediction via MatterSim, and coordinated orchestration across all stages. We propose the first dedicated STEM2Mat-Bench for this task and evaluate performance using lattice RMSD, formation energy MAE, and structure-matching success rate. By orchestrating external tool calls, AutoMat enables a text-only LLM to outperform vision-language models in this domain, achieving closed-loop reasoning throughout the pipeline. In large-scale experiments over 450 structure samples, AutoMat substantially outperforms existing multimodal large language models and tools. These results validate both AutoMat and STEM2Mat-Bench, marking a key step toward bridging microscopy and atomistic simulation in materials science.The code and dataset are publicly available at https://github.com/yyt-2378/AutoMat and https://huggingface.co/datasets/yaotianvector/STEM2Mat.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12650
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use
Yang, Yaotian
Tang, Yiwen
Chen, Yizhe
Chen, Xiao
Qiu, Jiangjie
Xiong, Hao
Yin, Haoyu
Luo, Zhiyao
Zhang, Yifei
Tao, Sijia
Li, Wentao
Zhang, Qinghua
Li, Yuqiang
Ouyang, Wanli
Zhao, Bin
Wang, Xiaonan
Wei, Fei
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine learning-based interatomic potentials and force fields depend critically on accurate atomic structures, yet such data are scarce due to the limited availability of experimentally resolved crystals. Although atomic-resolution electron microscopy offers a potential source of structural data, converting these images into simulation-ready formats remains labor-intensive and error-prone, creating a bottleneck for model training and validation. We introduce AutoMat, an end-to-end, agent-assisted pipeline that automatically transforms scanning transmission electron microscopy (STEM) images into atomic crystal structures and predicts their physical properties. AutoMat combines pattern-adaptive denoising, physics-guided template retrieval, symmetry-aware atomic reconstruction, fast relaxation and property prediction via MatterSim, and coordinated orchestration across all stages. We propose the first dedicated STEM2Mat-Bench for this task and evaluate performance using lattice RMSD, formation energy MAE, and structure-matching success rate. By orchestrating external tool calls, AutoMat enables a text-only LLM to outperform vision-language models in this domain, achieving closed-loop reasoning throughout the pipeline. In large-scale experiments over 450 structure samples, AutoMat substantially outperforms existing multimodal large language models and tools. These results validate both AutoMat and STEM2Mat-Bench, marking a key step toward bridging microscopy and atomistic simulation in materials science.The code and dataset are publicly available at https://github.com/yyt-2378/AutoMat and https://huggingface.co/datasets/yaotianvector/STEM2Mat.
title AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.12650