EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Empowering Generalist Material Intelligence with Large Language Models

Wenhao Yuan, Guangyao Chen, Zhilong Wang, Fengqi You iD

Advanced Materials · 2025-08 · 37 (32)

DOI: 10.1002/adma.202502771 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Advanced Materials, online erschienen am 12.05.2025. Verfasst von Wenhao Yuan und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Engineering, Cornell University, Ithaca, NY, 14853, USA. Hauptthemen laut MEDLINE: Language, Artificial Intelligence, Materials Science. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 323 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) are steering the development of generalist materials intelligence (GMI), a unified framework integrating conceptual reasoning, computational modeling, and experimental validation. Central to this framework is the agent‐in‐the‐loop paradigm, where LLM‐based agents function as dynamic orchestrators, synthesizing multimodal knowledge, specialized models, and experimental robotics to enable fully autonomous discovery. Drawing from a comprehensive review of LLMs’ transformative impact across representative applications in materials science, including data extraction, property prediction, structure generation, synthesis planning, and self‐driven labs, this study underscores how LLMs are revolutionizing traditional tasks, catalyzing the agent‐in‐the‐loop paradigm, and bridging the ontology‐concept‐computation‐experiment continuum. Then the unique challenges of scaling up LLM adoption are discussed, particularly those arising from the misalignment of foundation LLMs with materials‐specific knowledge, emphasizing the need to enhance adaptability, efficiency, sustainability, interpretability, and trustworthiness in the pursuit of GMI. Nonetheless, it is important to recognize that LLMs are not universally efficient. Their substantial resource demands and inconsistent performance call for careful deployment based on demonstrated task suitability. To address these realities, actionable strategies and a progressive roadmap for equitably and democratically implementing materials‐aware LLMs in real‐world practices are proposed.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LanguageArtificial IntelligenceMaterials ScienceLarge Language Models

Stichwörter der Autor:innen

autonomous agentsgenerative artificial intelligencelarge language modelsmaterial intelligence

Autor:innen und Institutionen

  • College of Engineering, Cornell University, Ithaca, NY, 14853, USA.
  • Cornell University AI for Science Institute (CUAISci), Cornell University, Ithaca, NY, 14853, USA.
  • Robert Frederick Smith School of Chemical and Biomolecular Engineering, Cornell University, Ithaca, NY, 14853, USA.

ORCID-Profile: Fengqi You

Zitieren

APA

Yuan, W., Chen, G., Wang, Z., & You, F. (2025). Empowering Generalist Material Intelligence with Large Language Models. Advanced Materials, 37(32). https://doi.org/10.1002/adma.202502771

Vancouver

Yuan W, Chen G, Wang Z, You F. Empowering Generalist Material Intelligence with Large Language Models. Advanced Materials. 2025;37(32). doi:10.1002/adma.202502771

BibTeX
@article{Yuan2025,
  author = {Yuan, Wenhao and Chen, Guangyao and Wang, Zhilong and You, Fengqi},
  title = {Empowering Generalist Material Intelligence with Large Language Models},
  journal = {Advanced Materials},
  year = {2025},
  volume = {37},
  number = {32},
  doi = {10.1002/adma.202502771}
}
Kostenlos starten →