AI自主优化晶体图网络，精准预测材料带隙。
Optimizing Expert-Designed Crystal Graph Networks for Band-Gap Prediction with an Autonomous LLM Research Loop
- 用LLM代理自动优化专家设计的晶体图网络结构。
- 在MatBench上超越17个专家模型，达最优性能。
- 适合关注自研AI科研与材料计算的学者。
从结构预测材料性质是计算材料科学中的核心且快速发展的课题。十年来已建立公开基准和多种机器学习模型（Dunn et al., 2020）。该任务具有固定评价指标和基准，天然适合自主智能体研究（Karpathy, 2026）。在包含超过10万种晶体的MatBench带隙基准上，一个通用编码代理自主构建出无需外部预训练的最准确模型，超越了所有17个报告的专家设计模型。深入分析显示，其成功源于实现已知方法：或已在晶体神经网络中标准使用，或借鉴自其他机器学习领域。关键实现包括每条消息传递边上的元素对特征，以及晶格空间群嵌入。该工作不仅证明了LLM代理可优化专家设计的材料性质预测模型，也探讨了此类自主研究的局限性。
原文摘要 · Abstract (English)
Predicting a material's properties from its structure is a central, fast-advancing problem in computational materials science. A decade of work has produced standard public benchmarks and many published machine-learning models for the task (Dunn et al., 2020). The task's fixed metric and these baselines make it a natural setting for autonomous agent research (Karpathy, 2026). On the MatBench band-gap benchmark ($>$100k crystals), a general-purpose coding agent autonomously built the most accurate model trained without external pretraining, ahead of all seventeen expert-designed models reported for the task. A closer analysis shows it reached this by implementing known methods: either already standard in crystal neural-network models, or borrowed from other areas of machine learning. The contributing implementations include element-pair features on each message-passing edge and a crystal space-group embedding. The work not only demonstrates that LLM-agent autonomous research can optimize an expert-designed machine learning model for material property prediction, but also investigates the limitations of such autonomous research.
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。