A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools
- 1Electrical Engineering and Computer Science, University of Arkansas
- 2Computer Science, Baylor University
Abstract
Foundation models (FMs) are catalyzing a transformative shift in materials science (MatSci) by enabling scalable, general-purpose, and multimodal AI systems for scientific discovery. Unlike traditional ML models, which are typically narrow in scope and require task-specific engineering, FMs offer cross-domain generalization and exhibit emergent capabilities. Their versatility is especially well-suited to materials science, where research challenges span diverse data types and scales. This survey provides a comprehensive overview of foundation models, agentic systems, datasets, and computational tools supporting this growing field. We introduce a task-driven taxonomy encompassing six broad application areas: data extraction, interpretation and Q&A; atomistic simulation; property prediction; materials structure, design and discovery; process planning, discovery, and optimization; and multiscale modeling. We discuss recent advances in both unimodal and multimodal FMs, as well as emerging large language model (LLM) agents. Furthermore, we review standardized datasets, open-source tools, and autonomous experimental platforms that collectively fuel the development and integration of FMs into research workflows. We assess the early successes of foundation models and identify persistent limitations, including challenges in generalizability, interpretability, data imbalance, safety concerns, and limited multimodal fusion. Finally, we articulate future research directions centered on scalable pretraining, continual learning, data governance, and trustworthiness.
Related
- Domain-Informed AI Multimodal Foundation Model for Materials Science
- Large Language Models in Chemistry and Materials Science: A Comprehensive Survey
- From Execution to Discovery : Physical Verification as the Key Gap in AI Agents for Science
- AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.org
- Realistic Simulations of Energy Materials Using Foundation Models and Electrode-Potential Learning
BibTeX
@article{van2026survey,
title = {{A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools}},
author = {Minh-Hao Van and Prateek Verma and Chen Zhao and Xintao Wu},
journal = {ACM Computing Surveys},
year = {2026},
month = jun,
doi = {10.1145/3822503},
url = {https://doi.org/10.1145/3822503},
note = {CC BY},
}
RIS
TY - JOUR
TI - A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools
AU - Minh-Hao Van
AU - Prateek Verma
AU - Chen Zhao
AU - Xintao Wu
PY - 2026
DA - 2026/06/25
JO - ACM Computing Surveys
DO - 10.1145/3822503
UR - https://doi.org/10.1145/3822503
AB - Foundation models (FMs) are catalyzing a transformative shift in materials science (MatSci) by enabling scalable, general-purpose, and multimodal AI systems for scientific discovery. Unlike traditional ML models, which are typically narrow in scope and require task-specific engineering, FMs offer cross-domain generalization and exhibit emergent capabilities. Their versatility is especially well-suited to materials science, where research challenges span diverse data types and scales. This survey provides a comprehensive overview of foundation models, agentic systems, datasets, and computational tools supporting this growing field. We introduce a task-driven taxonomy encompassing six broad application areas: data extraction, interpretation and Q&A; atomistic simulation; property prediction; materials structure, design and discovery; process planning, discovery, and optimization; and multiscale modeling. We discuss recent advances in both unimodal and multimodal FMs, as well as emerging large language model (LLM) agents. Furthermore, we review standardized datasets, open-source tools, and autonomous experimental platforms that collectively fuel the development and integration of FMs into research workflows. We assess the early successes of foundation models and identify persistent limitations, including challenges in generalizability, interpretability, data imbalance, safety concerns, and limited multimodal fusion. Finally, we articulate future research directions centered on scalable pretraining, continual learning, data governance, and trustworthiness.
SN - 0360-0300
SN - 1557-7341
ER -