用AI自动验证材料科学假说，实现从猜想到仿真实验的闭环。
MIND: AI Co-Scientist for Material Research
- 构建多智能体系统，分阶段完成假设优化、仿真验证与辩论式评估。
- 集成SevenNet-Omni势函数，支持大规模分子动力学模拟验证。
- 提供网页界面，适合材料研究者快速测试新假设，可扩展性强。
大型语言模型（LLMs）已推动科学发现中代理型AI的发展，但多数方法仍局限于文本推理，缺乏自动化实验验证。本文提出MIND，一种基于LLM的材料科学研究自动化假说验证框架。MIND将科学发现流程组织为假设优化、实验验证与基于辩论的验证三阶段，采用多智能体架构。在实验验证环节，系统整合机器学习原子间势，特别是SevenNet-Omni，实现可扩展的虚拟实验。此外，我们还提供了基于网页的用户界面，支持自动化假说测试。模块化设计允许接入更多实验模块，适配更广泛的科研流程。代码开源于：https://github.com/IMMS-Ewha/MIND，演示视频见：https://youtu.be/lqiFe1OQzN4。
原文摘要 · Abstract (English)
Large language models (LLMs) have enabled agentic AI systems for scientific discovery, but most approaches remain limited to textbased reasoning without automated experimental verification. We propose MIND, an LLM-driven framework for automated hypothesis validation in materials research. MIND organizes the scientific discovery process into hypothesis refinement, experimentation, and debate-based validation within a multi-agent pipeline. For experimental verification, the system integrates Machine Learning Interatomic Potentials, particularly SevenNet-Omni, enabling scalable in-silico experiments. We also provide a web-based user interface for automated hypothesis testing. The modular design allows additional experimental modules to be integrated, making the framework adaptable to broader scientific workflows. The code is available at: https://github.com/IMMS-Ewha/MIND, and a demonstration video at: https://youtu.be/lqiFe1OQzN4.
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。