Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.11540 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913026101215232 |
|---|---|
| author | Shi, Tongyu Li, Yutang Li, Zhanyuan Liu, Qian Zhou, Jie Xu, Wenhe Li, Yang Dai, Dawei He, Rui Zhou, Wenhua Wang, Jiahong Yu, Xue-Feng |
| author_facet | Shi, Tongyu Li, Yutang Li, Zhanyuan Liu, Qian Zhou, Jie Xu, Wenhe Li, Yang Dai, Dawei He, Rui Zhou, Wenhua Wang, Jiahong Yu, Xue-Feng |
| contents | 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 with two synergistic models specialization for crystal materials research. MatBrain employs 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 confirms that this architecture resolves the conflict between tool planning and analytical reasoning by decoupling their distinct entropy dynamics. Enabled by this dual-model architecture and structural efficiency, MatBrain significantly outperforms larger general-purpose models while reducing the hardware deployment barrier by over 95%. 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 hours, achieving approximately 100-fold acceleration over traditional approaches. These results demonstrate the potential of lightweight collaborative intelligence for advancing materials research capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11540 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A collaborative agent with two lightweight synergistic models for autonomous crystal materials research Shi, Tongyu Li, Yutang Li, Zhanyuan Liu, Qian Zhou, Jie Xu, Wenhe Li, Yang Dai, Dawei He, Rui Zhou, Wenhua Wang, Jiahong Yu, Xue-Feng Artificial Intelligence 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 with two synergistic models specialization for crystal materials research. MatBrain employs 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 confirms that this architecture resolves the conflict between tool planning and analytical reasoning by decoupling their distinct entropy dynamics. Enabled by this dual-model architecture and structural efficiency, MatBrain significantly outperforms larger general-purpose models while reducing the hardware deployment barrier by over 95%. 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 hours, achieving approximately 100-fold acceleration over traditional approaches. These results demonstrate the potential of lightweight collaborative intelligence for advancing materials research capabilities. |
| title | A collaborative agent with two lightweight synergistic models for autonomous crystal materials research |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.11540 |