Reshaping MOFs text mining with a dynamic multi-agents framework of large language model
This system accelerates data-driven materials discovery for MOF researchers by replacing static database lookups with real-time extraction from literature.
The researchers tackled the challenge of extracting synthesis conditions for metal-organic frameworks (MOFs) from scattered and inconsistent literature by developing MOFh6, a large language model-driven system that converts raw articles into standardized synthesis tables with 99% extraction accuracy and 94.1% abbreviation resolution.
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 94.1% of abbreviation cases across five major publishers, and maintained a precision of 0.93 +/- 0.01. Processing a full text takes 9.6 s, locating synthesis descriptions 36 s, with 100 papers processed for USD 4.24. By replacing static database lookups with real-time extraction, MOFh6 reshapes MOF synthesis research, accelerating the conversion of literature knowledge into practical synthesis protocols and enabling scalable, data-driven materials discovery.