MatterMind: A User-Friendly Material Design Platform Assisted by Large Language Model

Abstract

Machine learning and AI assistants are reshaping materials research; however, their day-to-day application in experimental and computational workflows is still inconsistent, limited by insufficient software documentation and software engineering practices, fragmented software engineering ecosystem and brittle integration between computational tools. Especially in the field of materials informatics, the lack of user-friendly tool interfaces has restricted the popularization of data-driven methods in daily scientific research. In this study, we present MatterMind, a user-friendly agentic interface that closes the loop between first-principles computation, generative structure design, and large language model (LLM) analysis. The platform unifies (i) plane-wave first-principles workflows through Vienna Ab initio Simulation Package (VASP), (ii) crystal generation via diffusion models, and (iii) LLM assistance for error diagnosis, result interpretation, and report drafting. With simple “button-click” operations or natural-language prompts, users can: (1) build, launch, and monitor VASP jobs with automated parsing and recovery; (2) sample candidate crystals using modern generative models (MatterGen); and (3) obtain LLM-guided summaries, comparisons, and next-step suggestions for screening decisions. We illustrate end-to-end case studies that couple crystal generation to DFT relaxation and LLM-assisted assessment, reducing scripting overhead and improving transparency and reuse from a software engineering perspective. It provides an intelligent scientific tool with comprehensive software documentation, enhancing the efficiency and reliability of scientific exploration in chemical and materials science research.

Keywords

AI for science / large language models / materials design / Materials Genome / software

References

[1] H. Ge, J. Liu, M. Sebek, et al., “AI-Assisted Wafer-Scale Exfoliation and Transfer of 2D Materials: Status, Challenges and Perspectives,” AI for Science 1, no. 1 (2025): 013002, https://doi.org/10.1088/3050-287X/ae0353.

[2] W. Y. Wang, S. Zhang, G. Li, et al., “Artificial Intelligence Enabled Smart Design and Manufacturing of Advanced Materials: The Endless Frontier in AI⁺ Era,” Materials Genome Engineering Advances 2, no. 3 (2024): e56, https://doi.org/10.1002/mgea.56.

[3] Y. Qi and W. Yang, “From Data to Discovery: How AI-Driven Materials Databases Are Reshaping Research,” Computers, Materials & Continua 83, no. 2 (2025): 1555–1559, https://doi.org/10.32604/cmc.2025.064061.

[4] Z. Chen and Y. Yang, “Data-Driven Design of Eutectic High Entropy Alloys,” Journal of Materials Informatics 3, no. 2 (2023): 10, https://doi.org/10.20517/jmi.2023.06.

[5] M. W. Gaultois, T. D. Sparks, C. K. H. Borg, R. Seshadri, W. D. Bonificio, and D. R. Clarke, “Data-Driven Review of Thermoelectric Materials: Performance and Resource Considerations,” Chemistry of Materials 25, no. 15 (2013): 2911–2920, https://doi.org/10.1021/cm400893e.

[6] Y. Huang, L. Zhang, H. Deng, and J. Mao, “NJmat: Data-Driven Machine Learning Interface to Accelerate Material Design,” Journal of Chemical Information and Modeling 64, no. 16 (2024): 6477–6491, https://doi.org/10.1021/acs.jcim.4c00493.

[7] J. M. Cole, “A Design-to-Device Pipeline for Data-Driven Materials Discovery,” Accounts of Chemical Research 53, no. 3 (2020): 599–610, https://doi.org/10.1021/acs.accounts.9b00470.

[8] T. Lu, M. Li, W. Lu, and T.-Y. Zhang, “Recent Progress in the Data-Driven Discovery of Novel Photovoltaic Materials,” Journal of Materials Informatics 2, no. 2 (2022): 7, https://doi.org/10.20517/jmi.2022.07.

[9] J. Xie, “Prospects of Materials Genome Engineering Frontiers,” Materials Genome Engineering Advances 1, no. 2 (2023): e17, https://doi.org/10.1002/mgea.17.

[10] J. J. de Pablo, N. E. Jackson, M. A. Webb, et al., “New Frontiers for the Materials Genome Initiative,” npj Computational Materials 5, no. 1 (2019): 41, https://doi.org/10.1038/s41524-019-0173-4.

[11] Y. Shang, Z. Xiong, K. An, J. A. Hauch, C. J. Brabec, and N. Li, “Materials Genome Engineering Accelerates the Research and Development of Organic and Perovskite Photovoltaics,” Materials Genome Engineering Advances 2, no. 1 (2024): e28, https://doi.org/10.1002/mgea.28.

[12] D. Vergara, A. del Bosque, and P. Fernández-Arias, “A Decade of Digital Twins in Materials Science and Engineering,” Computers, Materials & Continua 85, no. 1 (2025): 41–64, https://doi.org/10.32604/cmc.2025.067881.

[13] Y. Liu, Y. Cui, H. Zhou, et al., “Machine Learning-Based Methods for Materials Inverse Design: A Review,” Computers, Materials & Continua 82, no. 2 (2025): 1463–1492, https://doi.org/10.32604/cmc.2025.060109.

[14] Y. Shen, S. Zhao, Y. Lv, F. Chen, L. Fu, and H. Karimi-Maleh, “Large Language Model-Driven Knowledge Discovery for Designing Advanced Micro/Nano Electrocatalyst Materials,” Computers, Materials & Continua 84, no. 2 (2025): 1921–1950, https://doi.org/10.32604/cmc.2025.067427.

[15] Z. Wang, A. Chen, K. Tao, Y. Han, and J. Li, “MatGPT: A Vane of Materials Informatics From Past, Present, to Future,” Advanced Materials 36, no. 6 (2024): 2306733, https://doi.org/10.1002/adma.202306733.

[16] J. Yuan, Z. Li, Y. Yang, et al., “Applications of Machine Learning Method in High-Performance Materials Design: A Review,” Journal of Materials Informatics 4, no. 3 (2024): 1–3, https://doi.org/10.20517/jmi.2024.15.

[17] Y.-C. Hu, “Data-Driven Prediction of the Glass-Forming Ability of Modeled Alloys by Supervised Machine Learning,” Journal of Materials Informatics 3, no. 1 (2023): 1, https://doi.org/10.20517/jmi.2022.28.

[18] N. C. Nguyen and A. Rohskopf, “Proper Orthogonal Descriptors for Efficient and Accurate Interatomic Potentials,” Journal of Computational Physics 480 (2023): 112030, https://doi.org/10.1016/j.jcp.2023.112030.

[19] Y. Huang and L. Zhang, “Descriptor Design for Perovskite Material With Compatible Molecules via Language Model and First-Principles,” Journal of Chemical Theory and Computation 20, no. 15 (2024): 6790–6800, https://doi.org/10.1021/acs.jctc.4c00465.

[20] P. R. Linnebank, D. A. Poole, A. M. Kluwer, and J. N. H. Reek, “A Substrate Descriptor Based Approach for the Prediction and Understanding of the Regioselectivity in Caged Catalyzed Hydroformylation,” Faraday Discussions 244 (2023): 169–185, https://doi.org/10.1039/D3FD00023K.

[21] S. Zhai, H. Xie, P. Cui, et al., “A Combined Ionic Lewis Acid Descriptor and Machine-Learning Approach to Prediction of Efficient Oxygen Reduction Electrodes for Ceramic Fuel Cells,” Nature Energy 7, no. 9 (2022): 866–875, https://doi.org/10.1038/s41560-022-01098-3.

[22] M. Waskom, “Seaborn: Statistical Data Visualization,” Journal of Open Source Software 6, no. 60 (2021): 3021, https://doi.org/10.21105/joss.03021.

[23] R. Choudhury, M. Aykol, S. Gratzl, J. Montoya, and J. Hummelshøj, “MaterialNet: A Web-Based Graph Explorer for Materials Science Data,” Journal of Open Source Software 5, no. 47 (2020): 2105, https://doi.org/10.21105/joss.02105.

[24] B. Huang, G. F. von Rudorff, and O. A. von Lilienfeld, “The Central Role of Density Functional Theory in the AI Age,” Science 381, no. 6654 (2023): 170–175, https://doi.org/10.1126/science.abn3445.

[25] V. Gupta, K. Choudhary, Y. Mao, et al., “MPpredictor: An Artificial Intelligence-Driven Web Tool for Composition-Based Material Property Prediction,” Journal of Chemical Information and Modeling 63, no. 7 (2023): 1865–1871, https://doi.org/10.1021/acs.jcim.3c00307.

[26] W. Wang and G.-M. Rignanese, “AI for Science to Serve the AI-Driven Scientific Innovation,” AI for Science 1, no. 1 (2025): 010201, https://doi.org/10.1088/3050-287X/add0cb.

[27] J. He, H. Guan, W. Feng, et al., “Controlling Risks of AI in Chemical Science With Agents,” AI for Science 1, no. 1 (2025): 015002, https://doi.org/10.1088/3050-287X/adfee5.

[28] Y. Yang, L. Cao, J. Ren, W. Gao, and S. Ling, “Artificial Intelligence for Fibrous Network Design and Mechanics,” AI for Science 1, no. 1 (2025): 012001, https://doi.org/10.1088/3050-287X/adfaf7.

[29] V. Wang, N. Xu, J.-C. Liu, G. Tang, and W.-T. Geng, “VASPKIT: A User-Friendly Interface Facilitating High-Throughput Computing and Analysis Using VASP Code,” Computer Physics Communications 267 (2021): 108033, https://doi.org/10.1016/j.cpc.2021.108033.

[30] L. Wei, Q. Li, Y. Song, et al., “Crystal Composition Transformer: Self-Learning Neural Language Model for Generative and Tinkering Design of Materials,” Advanced Science 11, no. 36 (2024): 2304305, https://doi.org/10.1002/advs.202304305.

[31] J. Ma, B. Cao, S. Dong, et al., “MLMD: A Programming-Free AI Platform to Predict and Design Materials,” npj Computational Materials 10, no. 1 (2024): 59, https://doi.org/10.1038/s41524-024-01243-4.

[32] C. Zeni, R. Pinsler, D. Zügner, et al., “A Generative Model for Inorganic Materials Design,” Nature 639, no. 8055 (2025): 624–632, https://doi.org/10.1038/s41586-025-08628-5.

Rights & permissions

2026 The Author(s). Materials Genome Engineering Advances published by Wiley-VCH GmbH on behalf of University of Science and Technology Beijing.