Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductor Discovery
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914527108399104 |
|---|---|
| author | Li, Mingze Rong, Yu Li, Songyou Wang, Lihong Cen, Jiacheng Wu, Liming Li, Anyi Li, Zongzhao Liu, Qiuliang Jiao, Rui Bian, Tian Wang, Pengju Sun, Hao Zhang, Jianfeng Wen, Ji-Rong Zhao, Deli Jin, Shifeng Xu, Tingyang Huang, Wenbing |
| author_facet | Li, Mingze Rong, Yu Li, Songyou Wang, Lihong Cen, Jiacheng Wu, Liming Li, Anyi Li, Zongzhao Liu, Qiuliang Jiao, Rui Bian, Tian Wang, Pengju Sun, Hao Zhang, Jianfeng Wen, Ji-Rong Zhao, Deli Jin, Shifeng Xu, Tingyang Huang, Wenbing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_23758 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductor Discovery Li, Mingze Rong, Yu Li, Songyou Wang, Lihong Cen, Jiacheng Wu, Liming Li, Anyi Li, Zongzhao Liu, Qiuliang Jiao, Rui Bian, Tian Wang, Pengju Sun, Hao Zhang, Jianfeng Wen, Ji-Rong Zhao, Deli Jin, Shifeng Xu, Tingyang Huang, Wenbing Machine Learning Materials Science 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. |
| title | Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductor Discovery |
| topic | Machine Learning Materials Science |
| url | https://arxiv.org/abs/2604.23758 |