32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery

Large language models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications of LLMs through 32 total projects developed during the second annual LLM hackathon for applications in materials science and chemistry, a global hybrid event. These projects spanned seven key research areas: (1) molecular and material property prediction, (2) molecular and material design, (3) automation and novel interfaces, (4) scientific communication and education, (5) research data management and automation, (6) hypothesis generation and evaluation, and (7) knowledge extraction and reasoning from the scientific literature. Collectively, these applications illustrate how LLMs serve as versatile predictive models, platforms for rapid prototyping of domain-specific tools, and much more. In particular, improvements in both open source and proprietary LLM performance through the addition of reasoning, additional training data, and new techniques have expanded effectiveness, particularly in low-data environments and interdisciplinary research. As LLMs continue to improve, their integration into scientific workflows presents both new opportunities and new challenges, requiring ongoing exploration, continued refinement, and further research to address reliability, interpretability, and reproducibility.

Authors

Institutions

Publication Details

Journal
Machine Learning Science and Technology
Published
2025-08-29
DOI
https://doi.org/10.1088/2632-2153/ae011a
Citations
6
Primary Topic
Machine Learning in Materials Science
Type
article
Field-Weighted Citation Impact
3.11

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery

Aleyna Beste Ozhan, Joshua D. Bocarsly, Jan Janßen, Aakash Ashok Naik et al.
6 citations
Machine Learning Science and Technology
Machine Learning in Materials Science
3.11
article

32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery

Aleyna Beste Ozhan, Joshua D. Bocarsly, Jan Janßen, Aakash Ashok Naik, L. Catherine Brinson, Nathan Daelman, Abhijeet Gangan, Philippe Schwaller, Ian Foster, Ben Blaiszik, Yuan Chiang, Soroush Mahjoubi, Min–Hsueh Chiu, Seyed Mohamad Moosavi, Hassan Harb, Defne Çırcı, Mehrad Ansari, Katharina Ueltzen, Sascha Klawohn, Matthew L. Evans, Dieter Plessers, Janine George, Calvin Li, Ghazal Khalighinejad, Alexander Al‐Feghali, Yoel Zimmermann, Yue Wu, Aritra Roy, Sartaaj Takrim Khan, Carla Terboven, Adib Bazgir, Magdalena Lederbauer, Bernadette Mohr, Fabian Schöppach, Shang Zhu
article en
6 citations

Abstract

Large language models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications of LLMs through 32 total projects developed during the second annual LLM hackathon for applications in materials science and chemistry, a global hybrid event. These projects spanned seven key research areas: (1) molecular and material property prediction, (2) molecular and material design, (3) automation and novel interfaces, (4) scientific communication and education, (5) research data management and automation, (6) hypothesis generation and evaluation, and (7) knowledge extraction and reasoning from the scientific literature. Collectively, these applications illustrate how LLMs serve as versatile predictive models, platforms for rapid prototyping of domain-specific tools, and much more. In particular, improvements in both open source and proprietary LLM performance through the addition of reasoning, additional training data, and new techniques have expanded effectiveness, particularly in low-data environments and interdisciplinary research. As LLMs continue to improve, their integration into scientific workflows presents both new opportunities and new challenges, requiring ongoing exploration, continued refinement, and further research to address reliability, interpretability, and reproducibility.

Machine Learning Science and TechnologyVol. 6(3)
University of Southern California (US), Argonne National Laboratory (US), Federal Institute For Materials Research and Testing (DE), Lawrence Berkeley National Laboratory (US), University of California, Los Angeles (US), Duke University (US), University of Toronto (CA), University of Michigan (US), Helmholtz-Zentrum Berlin für Materialien und Energie (DE), TiGenix (Spain) (ES), London South Bank University (GB), ETH Zurich (CH), Humboldt-Universität zu Berlin (DE), University of Chicago (US), Max-Planck-Institut für Nachhaltige Materialien (DE), Ann Arbor Center for Independent Living (US), Boston Fusion (United States) (US), University of Houston (US), McGill University (CA), École Polytechnique Fédérale de Lausanne (CH), Massachusetts Institute of Technology (US), Friedrich Schiller University Jena (DE), University of Missouri (US), University of Amsterdam (NL), University of California, Berkeley (US), UCLouvain (BE), KU Leuven (BE)
Office of Advanced Cyberinfrastructure, Material Measurement Laboratory
Openalex Percentile: Top 8%
Machine Learning in Materials Science
3.11
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.