用智能体融合原子与语言模型，加速超导材料发现。
Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductor Discovery
- 构建智能体框架，协同原子模型算数值、语言模型做语义推理。
- 28小时发现6.8万高置信度候选，红移超导数据库数个数量级。
- 实验证实4种新超导体，含从头生成与数据库隐含结构。
人工智能已通过高通量预测与生成加速材料发现，但决策问题仍是重大瓶颈。现有AI系统可提出数百万候选物，但确定可行实验目标需在原子尺度数值计算与高层语义推理间做出多维判断。本文提出ElementsClaw智能体框架，协调一系列基于10亿参数模型Elements微调的大型原子模型（LAM）进行数值计算，同时利用大型语言模型（LLM）进行语义推理。应用于超导体研究，ElementsClaw重新发现66种实验验证的超导体，这些物质未被标准SuperCon3D数据库收录。在240万平衡晶体规模下，仅用28 GPU小时识别出68,000个高置信度候选，相比历时数十年人工整理的数据集，显著扩展了已知超导空间。受智能体推理引导，我们实验合成了四种新型超导体：构型引导的Zr₃ScRe₈（Tc = 6.5 K）、从头生成的HfZrRe₄（Tc = 5.9 K）、结构重释的Zr₄VRe₇（Tc = 3.5 K），以及数据库隐含的Hf₂₁Re₂₅（Tc = 2.5 K）。本研究建立了一个知识融合、自主协同、实验验证的材料发现新范式。
原文摘要 · Abstract (English)
Artificial intelligence has accelerated materials discovery through high-throughput prediction and generation, yet the decision problem remains a formidable bottleneck. While current AI systems readily propose millions of candidates, navigating the decision regarding a viable experimental target requires resolving multi-dimensional judgments across atomic-scale numerical computation and high-level semantic reasoning. Here we present ElementsClaw, an agentic framework for materials discovery that orchestrates a suite of Large Atomic Model (LAM) tools finetuned from our proposed 1-billion-parameter model Elements for numerical computation, while leveraging Large Language Models (LLMs) for semantic reasoning. Applied to superconductors, ElementsClaw rediscovers 66 experimentally verified superconductors that are absent from the standard SuperCon3D database. Scaling to 2.4 million equilibrium crystals, ElementsClaw identifies 68,000 high-confidence candidates in just 28 GPU hours (https://developer.damo-academy.com/material), expanding known superconducting space by orders of magnitude compared to datasets curated over decades. Guided by the agent's reasoning, we experimentally synthesize and verify four novel superconductors: the motif-guided Zr$_3$ScRe$_8$ ($T_c$ = 6.5 K), the de novo generated HfZrRe$_4$ ($T_c$ = 5.9 K), the structurally reinterpreted Zr$_4$VRe$_7$ ($T_c$ = 3.5 K), and the database-latent Hf$_{21}$Re$_{25}$ ($T_c$ = 2.5 K). Together, our results establish a knowledge integrated, autonomously orchestrated, and experimentally grounded paradigm for materials discovery.
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。