2026-09-14 中国科学院（CAS）
Researchers operate the AI system. (Image by SIAT)
＜関連情報＞
- https://english.cas.cn/newsroom/research-news/202609/t20260914_1200444.shtml
- https://www.nature.com/articles/s42256-026-01298-6
自律的な結晶材料研究のための、2つの軽量相乗効果モデルを備えた協調エージェント A collaborative agent with two lightweight synergistic models for autonomous crystal materials research
Tongyu Shi,Yutang Li,Zhanyuan Li,Qian Liu,Jie Zhou,Wenhe Xu,Yang Li,Dawei Dai,Rui He,Wenhua Zhou,Jiahong Wang & Xue-Feng Yu
Nature Machine Intelligence Published:10 September 2026
DOI:https://doi.org/10.1038/s42256-026-01298-6
Abstract
Current large language models require hundreds of billions of parameters yet struggle with domain-specific reasoning and tool coordination in materials science. Here we present MatBrain, a lightweight collaborative agent system comprising two synergistic models specialized for crystal materials research. MatBrain uses a dual-model architecture: Mat-R1 (30B parameters) as the analytical model providing expert-level domain reasoning, and Mat-T1 (14B parameters) as the executive model orchestrating tool-based actions. Entropy analysis reveals distinct output-distribution profiles for tool planning and analytical reasoning, providing a diagnostic signal consistent with the functional specialization of the two modules. Enabled by this dual-model architecture and structural efficiency, MatBrain is competitive with frontier large language models while being lightweight and locally deployable. MatBrain exhibits versatility across structure generation, property prediction and synthesis planning tasks. Applied to catalyst design, MatBrain generated 30,000 candidate structures and identified 38 promising materials within 48 h, while significantly reducing the human-active time required for materials design and computational screening. These results demonstrate the potential of lightweight collaborative intelligence for advancing materials research capabilities.
