轻量协同智能体加速晶体材料研发，效率超传统方法百倍。
A collaborative agent with two lightweight synergistic models for autonomous crystal materials research
- 双模型分工：300亿参数分析模型+140亿参数执行模型协同工作
- 48小时内生成3万种候选结构，发现38种新材料，提速约100倍
- 硬件需求降低95%以上，适合资源有限的研究团队使用
当前大语言模型需数百亿参数，但在材料科学领域仍难以胜任专业推理与工具协调。本文提出轻量级协同智能体MatBrain，由两个互补模型组成：300亿参数的Mat-R1作为分析模型，提供专家级领域推理；140亿参数的Mat-T1作为执行模型，负责工具调用与任务规划。熵分析表明，该架构通过解耦不同熵动态，有效缓解了工具规划与分析推理之间的冲突。得益于双模型架构与结构高效性，MatBrain在性能上显著超越更大规模通用模型，同时将硬件部署成本降低超过95%。系统在结构生成、性质预测与合成规划等任务中展现广泛适用性。应用于催化剂设计时，48小时内生成30,000个候选结构，识别出38种有前景材料，相较传统方法实现约100倍加速。结果证明，轻量协同智能是提升材料研究能力的有效路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。