SyncAI.news, a Varaisys broadcasting
Building verifiable databases at scale from the chemical literature via a multi-agent system
YC

Yufan Chen, Ching Ting Leung, Bowen Yu, Haifan Zhou, Jianwei Sun, Yong Huang, Linyan Li, Hao Chen, Hanyu Gao

· 1 min read

ResearcharXiv cs.AI

Building verifiable databases at scale from the chemical literature via a multi-agent system

arXiv:2507.20230v4 Announce Type: replace Abstract: Accelerating chemical research with artificial intelligence requires high-quality databases. However, many reactions exist only as graphics drawn for human readers, which machines must read exactly. Specialist software is precise but rigid, whereas multimodal language models are flexible yet often write incorrect structures; neither flags errors. We present ChemEAGLE, a multi-agent system where tools supply structures and a language model extends their reach through judgments that programs apply. On 424 published graphics, its F1 score for exactly correct reactions was 82.2%, against 47.7% for a tool-equipped generalist agent, and calibrated confidence limited review to 35% of reactions at 96.6% accuracy. Without review, it built a 60,103-reaction photochemistry database whose records trained models to rank conditions and predict products. Verifiable databases can thus be built at scale.

Original source

This story was published by arXiv cs.AI and written by Yufan Chen, Ching Ting Leung, Bowen Yu, Haifan Zhou, Jianwei Sun, Yong Huang, Linyan Li, Hao Chen, Hanyu Gao. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News