"DIVE" into Hydrogen Storage Materials Discovery with AI Agents

TL;DR

This paper introduces DIVE, an AI multi-agent workflow that extracts experimental data from scientific literature to accelerate the discovery of hydrogen storage materials, significantly improving data accuracy and enabling rapid inverse design.

Contribution

The paper presents DIVE, a novel AI system that systematically extracts structured data from unstructured scientific figures, enhancing materials discovery processes.

Findings

DIVE improves data extraction accuracy by 10-15% over commercial models.

It achieves over 30% better coverage than open-source models.

The workflow can identify new hydrogen storage materials in two minutes.

Abstract

Data-driven artificial intelligence (AI) approaches are fundamentally transforming the discovery of new materials. Despite the unprecedented availability of materials data in the scientific literature, much of this information remains trapped in unstructured figures and tables, hindering the construction of large language model (LLM)-based AI agent for automated materials design. Here, we present the Descriptive Interpretation of Visual Expression (DIVE) multi-agent workflow, which systematically reads and organizes experimental data from graphical elements in scientific literatures. We focus on solid-state hydrogen storage materials-a class of materials central to future clean-energy technologies and demonstrate that DIVE markedly improves the accuracy and coverage of data extraction compared to the direct extraction by multimodal models, with gains of 10-15% over commercial models and over 30% relative to open-source models. Building on a curated database of over 30,000 entries from 4,000 publications, we establish a rapid inverse design workflow capable of identifying previously unreported hydrogen storage compositions in two minutes. The proposed AI workflow and agent design are broadly transferable across diverse materials, providing a paradigm for AI-driven materials discovery.