From large language models to AI agents in energy materials research: enabling discovery, design, and automation
AI Agent · 19.12.2025 · 1 (1)
DOI: 10.20517/aiagent.2025.03 ↗Kurz gefasst
Fachartikel in der Zeitschrift AI Agent, online erschienen am 19.12.2025. Verfasst von Tongao Yao und 7 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 100 Literaturangaben.
Abstract (Originalsprache)
Fragmented knowledge and slow experimental iteration constrain the discovery of energy materials. We trace the evolution of artificial intelligence (AI) in materials science, from large language models as knowledge assistants to autonomous agents that can reason, plan, and use tools. We introduce a two-path framework to analyze this evolution, distinguishing architectural innovation (agent collaboration) from cognitive innovation (learning and representation). This framework synthesizes recent progress in AI-driven discovery, design, and automation. By examining challenges in reliability, interpretability, and physical grounding, we outline a roadmap toward physics-informed, human-AI systems for autonomous scientific discovery.
Zitieren
APA
Yao, T., Huang, J., Yan, Y., Yang, Y., Wang, Z., Shao, X., Gao, Z., & Yang, W. (2025). From large language models to AI agents in energy materials research: enabling discovery, design, and automation. AI Agent, 1(1). https://doi.org/10.20517/aiagent.2025.03
Vancouver
Yao T, Huang J, Yan Y, Yang Y, Wang Z, Shao X, et al. From large language models to AI agents in energy materials research: enabling discovery, design, and automation. AI Agent. 2025;1(1). doi:10.20517/aiagent.2025.03
BibTeX
@article{Yao2025,
author = {Yao, Tongao and Huang, Junming and Yan, Yujie and Yang, Yang and Wang, Ziye and Shao, Xuqiang and Gao, Zhengyang and Yang, Weijie},
title = {From large language models to AI agents in energy materials research: enabling discovery, design, and automation},
journal = {AI Agent},
year = {2025},
volume = {1},
number = {1},
doi = {10.20517/aiagent.2025.03}
}
EUVIMED