Alibaba’s Elements Claw AI agent unearths 4 new superconductors

Published: 7:30pm, 3 Jul 2026

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 (ElementsClaw), 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 (Elements) 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.

Four entirely new superconducting materials were successfully synthesized and verified in laboratory experiments:

• Hf21Re25 — a “missed discovery” retrieved from existing databases (Tc = 2.5 K)
• Zr4VRe7 — successfully validated after correcting a configuration error in the database (Tc = 3.5 K)
• HfZrRe4 — designed from scratch by the AI (Tc = 5.9 K)
• Zr3ScRe8 — derived by drawing inferences from similar structures (Tc = 6.5 K, highest critical temperature)

The predictive model achieved an AUC of 0.996 for determining superconductivity, with critical temperature prediction errors within 1K.

ElementsClaw also rediscovered 66 experimentally verified superconductors absent from the standard SuperCon3D database.

Rong Yu, Head of Scientific Intelligence at DAMO Academy, stated these are the first batch of superconducting materials discovered through this agentic framework. DAMO Academy has open-sourced the entire database of 2.4 million stable crystals predicted by ElementsClaw for academic use.

The research is presented at ICML 2026 and published on arXiv as “Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductor Discovery.”