ComProScanner: a multi-agent based framework for composition-property structured data extraction from scientific literature

2026/01/01 by Aritra Roy, Enrico Grisan, John Buckeridge +1 · 1 voice
Chemical Engineering · Materials Science · #Catalysis and Oxidation Reactions #Machine Learning in Materials Science #X-ray Diffraction in Crystallography

paper · pdf · doi:10.1039/d5dd00521c

openalex publication_date 2026/01/01 · openalex created_date 2026/03/26 · openalex updated_date 2026/06/11

Abstract

ComProScanner is an end-to-end multi-agentic autonomous platform that extracts, validates and visualises machine-readable compositions, properties and synthesis data from journal articles via Text and Data Mining APIs for database creation.

Discussions

• After months of work, ComProScanner is officially published in Digital Discovery as open access!🎉 A multi-agent AI framework that extracts composition-property data from scientific literature at sca [bsky, 2 points, 0 comments]

Related

• ComProScanner: A multi-agent based framework for composition-property structured data extraction from scientific literature
• Agents-K1: Towards Agent-native Knowledge Orchestration
• SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation
• MetaInfoSci: An Integrated Web Tool for Scholarly Data Analysis
• Agentic AutoSurvey: Let LLMs Survey LLMs