Engineering Papers⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 3676122

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

Zimmermann, Yoel (ORCID:0009000317204368)·Bazgir, Adib (ORCID:0000000164758505)·Al-Feghali, Alexander (ORCID:0009000483777049)·Ansari, Mehrad (ORCID:0000000156969193)·Bocarsly, Joshua (ORCID:000000027523152X)·Brinson, L. (ORCID:0000000325511563)·Chiang, Yuan (ORCID:0000000240177084)·Circi, Defne (ORCID:0000000257610198)·Chiu, Min-Hsueh (ORCID:0000000306377856)·Daelman, Nathan (ORCID:0000000276471816)·Evans, Matthew (ORCID:0000000211829098)·Gangan, Abhijeet·George, Janine (ORCID:0000000189070336)·Harb, Hassan (ORCID:0000000260163122)·Khalighinejad, Ghazal (ORCID:0009000524768043)·Takrim Khan, Sartaaj (ORCID:0009000921319700)·Klawohn, Sascha (ORCID:000000034850776X)·Lederbauer, Magdalena (ORCID:0009000806651839)·Mahjoubi, Soroush (ORCID:0000000188795431)·Mohr, Bernadette (ORCID:0000000309030073)·Mohamad Moosavi, Seyed (ORCID:0000000203575729)·Naik, Aakash (ORCID:0000000260716786)·Beste Ozhan, Aleyna (ORCID:0000000202813860)·Plessers, Dieter (ORCID:0000000189068447)·Roy, Aritra (ORCID:0000000302439124)·Schöppach, Fabian·Schwaller, Philippe (ORCID:0000000330466576)·Terboven, Carla (ORCID:0009000437860773)·Ueltzen, Katharina (ORCID:0009000329671182)·Wu, Yue (ORCID:0000000328748267)·Zhu, Shang (ORCID:0000000284338599)·Janssen, Jan (ORCID:0000000199487119)·Li, Calvin·Foster, Ian (ORCID:0000000321295269)·Blaiszik, Ben (ORCID:0000000253264902)
View original source ↗Read source document ↗Export metadata ↓

Abstract

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.

Explore related subjects

Computer ScienceScience & Technology - Other Topics

Keep this discovery

BibTeXRIS

Zimmermann, Yoel (ORCID:0009000317204368), Bazgir, Adib (ORCID:0000000164758505), Al-Feghali, Alexander (ORCID:0009000483777049), Ansari, Mehrad (ORCID:0000000156969193), Bocarsly, Joshua (ORCID:000000027523152X), Brinson, L. (ORCID:0000000325511563), Chiang, Yuan (ORCID:0000000240177084), Circi, Defne (ORCID:0000000257610198), Chiu, Min-Hsueh (ORCID:0000000306377856), Daelman, Nathan (ORCID:0000000276471816), Evans, Matthew (ORCID:0000000211829098), Gangan, Abhijeet, George, Janine (ORCID:0000000189070336), Harb, Hassan (ORCID:0000000260163122), Khalighinejad, Ghazal (ORCID:0009000524768043), Takrim Khan, Sartaaj (ORCID:0009000921319700), Klawohn, Sascha (ORCID:000000034850776X), Lederbauer, Magdalena (ORCID:0009000806651839), Mahjoubi, Soroush (ORCID:0000000188795431), Mohr, Bernadette (ORCID:0000000309030073), Mohamad Moosavi, Seyed (ORCID:0000000203575729), Naik, Aakash (ORCID:0000000260716786), Beste Ozhan, Aleyna (ORCID:0000000202813860), Plessers, Dieter (ORCID:0000000189068447), Roy, Aritra (ORCID:0000000302439124), Schöppach, Fabian, Schwaller, Philippe (ORCID:0000000330466576), Terboven, Carla (ORCID:0009000437860773), Ueltzen, Katharina (ORCID:0009000329671182), Wu, Yue (ORCID:0000000328748267), Zhu, Shang (ORCID:0000000284338599), Janssen, Jan (ORCID:0000000199487119), Li, Calvin, Foster, Ian (ORCID:0000000321295269), Blaiszik, Ben (ORCID:0000000253264902). 2025-09-29. 32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery. https://doi.org/10.1088/2632-2153/ae011a

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

Computer Science subjectScience & Technology - Other Topics subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related reports

DOE OSTI2023

Reconfigurable Cascaded Thermal Neuristors for Neuromorphic Computing

While the complementary metal-oxide semiconductor (CMOS) technology is the mainstream for the hardware implementation of neural networks, an alternative route is explored based on a new class of spiking oscillators called “thermal neuristors”, which operate and interact solely via thermal processes. Utilizing the insulator-to-metal transition (IMT) in vanadium dioxide, a wide variety of reconfigurable electrical dynamics mirroring biological neurons is demonstrated. Notably, inhibitory functionality is achieved just in a single oxide device, and cascaded information flow is realized exclusively through thermal interactions. To elucidate the underlying mechanisms of the neuristors, a detailed theoretical model is developed, which accurately reflects the experimental results. In conclusion, this study establishes the foundation for scalable and energy-efficient thermal neural networks, fostering progress in brain-inspired computing.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Using scalable computer vision to automate high-throughput semiconductor characterization

Abstract High-throughput materials synthesis methods, crucial for discovering novel functional materials, face a bottleneck in property characterization. These high-throughput synthesis tools produce 10 4 samples per hour using ink-based deposition while most characterization methods are either slow (conventional rates of 10 1 samples per hour) or rigid (e.g., designed for standard thin films), resulting in a bottleneck. To address this, we propose automated characterization (autocharacterization) tools that leverage adaptive computer vision for an 85x faster throughput compared to non-automated workflows. Our tools include a generalizable composition mapping tool and two scalable autocharacterization algorithms that: (1) autonomously compute the band gaps of 200 compositions in 6 minutes, and (2) autonomously compute the environmental stability of 200 compositions in 20 minutes, achieving 98.5% and 96.9% accuracy, respectively, when benchmarked against domain expert manual evaluation. These tools, demonstrated on the formamidinium (FA) and methylammonium (MA) mixed-cation perovskite system FA 1−x MA x PbI 3 , 0 ≤ x ≤ 1, significantly accelerate the characterization process, synchronizing it closer to the rate of high-throughput synthesis.

Science & Technology - Other Topics↗
DOE OSTI2024

Neuromorphic overparameterisation and few-shot learning in multilayer physical neural networks

Abstract Physical neuromorphic computing, exploiting the complex dynamics of physical systems, has seen rapid advancements in sophistication and performance. Physical reservoir computing, a subset of neuromorphic computing, faces limitations due to its reliance on single systems. This constrains output dimensionality and dynamic range, limiting performance to a narrow range of tasks. Here, we engineer a suite of nanomagnetic array physical reservoirs and interconnect them in parallel and series to create a multilayer neural network architecture. The output of one reservoir is recorded, scaled and virtually fed as input to the next reservoir. This networked approach increases output dimensionality, internal dynamics and computational performance. We demonstrate that a physical neuromorphic system can achieve an overparameterised state, facilitating meta-learning on small training sets and yielding strong performance across a wide range of tasks. Our approach’s efficacy is further demonstrated through few-shot learning, where the system rapidly adapts to new tasks.

Science & Technology - Other Topics↗