Knowledge-Guided Autonomous Discovery of Microenvironment-Tuned Metal–Organic Framework Photocatalysts

Here, we report an end-to-end workflow that couples literature-guided large-language-model (LLM) reasoning with real-time experimental feedback to propose, test, and refine microenvironment designs in MOF photocatalysts. The system mined and fused three domains (namely, photocatalytic H₂ production, hydrogenases and enzyme-mimetic catalysis) and deduced the hypothesis that placing basic, hydrogen-bonding groups near catalytic centers would facilitate water activation and proton transfer.

The hypothesis was instantiated by postsynthetic modification of UiO-67, generating 31 <b>Pt@UiO-67-X</b> variants and evaluating them across six closed-loop iterations on an automated platform. The search converged on <b>Pt@UiO-67-30</b> (8-quinolinecarboxylic acid), which delivered 2.33 mmol g^–1 h^–1, a ∼36-fold improvement over the parent material; in a larger, optimally illuminated reactor the same catalyst reached 12.48 mmol g^–1 h^–1 while preserving the library’s rank order.