Reshaping MOFs synthesis conditions mining with a dynamic multi-agents framework of large language model

Abstract

Accurately identifying the synthesis conditions of metal-organic frameworks (MOFs) is essential for guiding experimental design, yet remains challenging because relevant information in the literature is often scattered, inconsistent, and difficult to interpret. We present MOFh6, a large-language-model-driven system that reads raw articles or crystal codes and converts them into standardized synthesis tables. It links related descriptions across paragraphs, unifies ligand abbreviations with full names, and outputs structured parameters ready for use. MOFh6 achieved 99% extraction accuracy, resolved 90.8% of abbreviation cases across five major publishers, and maintained a precision of 0.93 ± 0.01. Processing a full text takes 9.6s, locating synthesis descriptions 36 s, with 100 papers processed for 4.24$. By replacing static database lookups with real-time extraction, MOFh6 reshapes MOFs synthesis research, accelerating the conversion of literature knowledge into practical synthesis protocols, enabling scalable, data-driven materials discovery. • LLM-powered MOFh6 unifies fragmented synthesis knowledge into structured data. • Transforms MOF synthesis informatics with scalable and cost-efficient workflow. • End-to-end system supports literature mining, structure query, and MOFs visualization. • 7 × faster processing, 76% lower cost, advancing MOF synthesis information discover.