AI RESEARCH
A Multi-Agent System Enables Versatile Information Extraction from the Chemical Literature
arXiv CS.AI
•
ArXi:2507.20230v3 Announce Type: replace To fully expedite AI-powered chemical research, high-quality chemical databases are the foundation. Automatic extraction of chemical information from the literature is essential for constructing reaction databases, but it is currently limited by the multimodality and style variability of chemical information. In this work, we developed a multimodal large language model (MLLM)-based multi-agent system for robust and automated chemical information extraction.