达摩院发布可发现超导体的 AI 智能体

阿里巴巴集团旗下达摩院发布了据称业界首个用于发现超导材料的人工智能智能体，并表示该工具已发现四种此前未知的化合物，随后在实验室实验中得到了验证。

超导

材料是指在冷却至低温时能够无电阻导电并排斥磁场的物质——这一能力上的突破可能彻底改变电力网络、量子计算和高速磁悬浮列车。

由于科学家仍缺乏预测超导性的完整理论框架，发现新型超导体长期以来一直依赖繁琐的试错实验。几十年来，研究人员在广泛使用的 SuperCon 数据库中仅积累了约 2000 种已知的超导材料。

据达摩院称，这款名为 Elements Claw 的 AI 智能体 旨在通过扫描科学文献并筛选数百万种晶体结构来提出候选材料供实验室验证，从而加速这一进程。

该系统由达摩院与中国人民大学及中国科学院大学合作开发。

Elements Claw 由一个专门的 10 亿参数基础模型驱动，该模型在 1.25 亿个分子和晶体结构上完成训练。它在 28 小时的 GPU 计算时间内筛选了 240 万种稳定晶体结构。

它识别出约 6.8 万个具有超导潜力的候选材料，随后将其范围缩小到最有希望进行物理测试的选项。

Alibaba Group Holding’s Damo Academy has unveiled what it calls the industry’s first artificial intelligence agent for discovering superconducting materials, saying that the tool has already found four previously unknown compounds that were later verified in laboratory experiments.

Superconducting

materials are substances able to conduct electricity without resistance and expel magnetic fields when cooled to low temperatures – a capability breakthrough that could revolutionise power grids, quantum computing and high-speed maglev trains.

Discovering new superconductors has long relied on laborious, trial-and-error experiments because scientists still lack a complete theoretical framework to predict superconductivity. Over the decades, researchers have only accumulated about 2,000 known superconducting materials in the widely used SuperCon database.

The

AI agent

, dubbed Elements Claw, was designed to accelerate the timeline by scanning scientific literature and screening millions of crystal structures to propose candidate materials for laboratory validation, according to Damo.

The system was developed in collaboration with Renmin University of China and the University of Chinese Academy of Sciences.

Powered by a specialised, one-billion-parameter foundation model trained on 125 million molecular and crystal structures, Elements Claw screened 2.4 million stable crystal structures in 28 hours of graphics processor computing time.

It identified about 68,000 candidates with superconducting potential, which it then narrowed down to the most promising options for physical testing.