LitMOF: An LLM Multi-Agent for Literature-Validated Metal-Organic Frameworks Database Correction and Expansion

TL;DR

LitMOF employs a large language model-based multi-agent system to validate, correct, and expand metal-organic frameworks databases by leveraging literature and crystallographic data, significantly improving data reliability.

Contribution

This work introduces LitMOF, a novel LLM-driven multi-agent framework that repairs structural errors and uncovers new MOFs, enhancing database accuracy and coverage.

Findings

Repaired 8,771 invalid MOF entries, covering 65.3% of non-computation-ready structures.

Uncovered 12,646 MOFs absent from existing databases, expanding the known design space.

Demonstrated that structural errors distort adsorption energy predictions and material rankings.

Abstract

Metal-organic framework (MOF) databases have grown rapidly through experimental deposition and large-scale literature extraction, but recent analyses show that nearly half of their entries contain substantial structural errors. These inaccuracies propagate through high-throughput screening and machine-learning workflows, limiting the reliability of data-driven MOF discovery. Correcting such errors is exceptionally difficult because true repairs require integrating crystallographic files, synthesis descriptions, and contextual evidence scattered across the literature. Here we introduce LitMOF, a large language model-driven multi-agent framework that validates crystallographic information directly from the original literature and cross-validates it with database entries to repair structural errors. Applying LitMOF to the experimental MOF database (the CSD MOF Subset), we constructed LitMOF-DB, a curated set of 186,773 computation-ready structures, including the successful repair of 8,771 invalid entries, which accounts for 65.3% of the not-computation-ready MOFs in the latest CoRE MOF database. Additionally, the system uncovered 12,646 experimentally reported MOFs absent from existing resources, substantially expanding the known experimental design space. Using direct air capture screening as a case study, we demonstrate that structural errors severely distort predicted adsorption energies and CO2/H2O selectivity, leading to systematic misranking of materials, false positives, and the omission of high-performance candidates. This work establishes a scalable pathway toward self-correcting scientific databases and a generalizable paradigm for LLM-driven curation in materials science.