To address the challenge of complex chemical spaces in solid-state battery research, we develop a research agent for automated solid electrolyte exploration, AutoSEE, which enables efficient end-to-end research, autonomously revealing design principles for high-performance solid electrolytes. By leveraging GPT-4o as a central controller, AutoSEE orchestrates specialized tools such as literature screening, text mining, and machine learning to construct specialized data sets and distill principles. Taking halide solid electrolytes as an example, AutoSEE processes 226 relevant articles with an average precision of 93.4% within 5 min and employs unsupervised clustering to autonomously distill a critical design principle that halide solid electrolytes featuring high charge density favor an amorphous phase and high ionic conductivity. Guided by this principle, we found an unexplored electrolyte LiTaB0.32O0.98Cl5, which possesses a high ionic conductivity (7.82 mS cm–1), experimentally validating the agent-distilled rule. AutoSEE showcases a paradigm shift from simple data retrieval to agentic knowledge exploration.
Luo et al. (Thu,) studied this question.