Application of agentic AI in composition-property-performance triad for refractories
B Sai PRAKASH, Shantanu SAHA, Biswajeet PAL, Arko CHAKRABORTHY, Mormee DAS
Abstract:Structure-property-processing remains an integral feature of metallurgical and material science design engineering. Agentic AI uses advanced large language models to access online literature to give estimates of properties based on composition , thus having a deep impact on performance estimation.Initial trials have revealed two such success cases. This has brought down the cost of trials, lab experiment costs and KPIs improvement of parameters such as service temperarure to the tune of 1.2 Cr
Keywords
Refractory, Large Language Models, Agentic AI
Published online 5/10/2026, 7 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: B Sai PRAKASH, Shantanu SAHA, Biswajeet PAL, Arko CHAKRABORTHY, Mormee DAS, Application of agentic AI in composition-property-performance triad for refractories, Materials Research Proceedings, Vol. 65, pp 8-14, 2026
DOI: https://doi.org/10.21741/9781644904138-2
The article was published as article 2 of the book Processing and Characterization of Materials
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] Chen, Y. et al., Agentic AI and Machine Learning for Accelerated Materials Discovery and Applications, arXiv, 2026.
[2] Gupta, A. et al., Artificial Intelligence in Materials by Design: From Informatics to Agentic Intelligence, Materials Today, 2025.
[3] Nematov, S., Hojamberdiev, M., Machine-Learning-Driven Materials Discovery, arXiv, 2025.
[4] Fu, H. et al., Machine Learning in Materials Science: Performance Prediction, Nanomaterials, 2022.
[5] Chen, Z. et al., ML-Assisted Multi-Element Optimization of Spinel Refractories, Materials, 2025.
[6] Ligezin, P., Pitak, M., Artificial Neural Networks in Ceramic and Refractory Materials, Refractories Journal, 2024. https://doi.org/10.35857/2663-3566.124.13
[7] Seyed Mahmoud, M. et al., ML-Based Design of Refractory Alloys for Thermal Conductivity, Materials, 2023.
[8] Sado, A. et al., Current State of Machine Learning for Refractory Properties, Metals, 2023.
[9] Brunner, S., Deep Learning for Refractory Ceramic Image Evaluation, Springer Nature Community, 2024.
[10] Advanced data mining and AI-based refractory wear prediction, Ceramics International, 2021.
[11] Wu, Z. et al., Machine-Learning-Driven Design of Refractory High-Entropy Alloys, Materials & Design, 2026.
[12] He, F. et al., ML-Assisted Design of RHEAs with Targeted Strength and Ductility, Acta Materialia, 2024.
[13] Xu, Y., Xu, C., ML-Based Multi-Objective Search for Refractory HEAs, Journal of Alloys and Compounds, 2025.
[14] Elkatatny, S., Machine Learning Synergy in High-Entropy Alloys, Journal of Materials Research and Technology, 2024. https://doi.org/10.1016/j.jmrt.2024.10.034
[15] Xie, Z. et al., AI Design of High-Entropy Alloys: Challenges and Opportunities, Metals, 2025. https://doi.org/10.3390/met15091012
[16] Giles, R. et al., Uncertainty Quantification in ML-Based RHEA Design, arXiv, 2023.
[17] Ghafarollahi, A., Buehler, M., Physics-Aware Multi-Agent AI for Alloy Design, MIT, 2025.
[18] Iyengar, A. et al., Composition-Based ML for Phase and Strength Prediction in RHEAs, arXiv, 2025.
[19] Catal, C. et al., Machine Learning-Assisted Alloy Design Systems, Computational Materials Science, 2024.
[20] Qi, J. et al., Integrated Design of Aluminum-Containing Refractory Alloys, arXiv, 2023.
