Metraipolis › archive › dc_a657cf746d20

RxnMiner: A Multimodal Agent for Structured Reaction Data Extraction from Chemistry Figures — arXiv:2611.02826

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02826
License (as archived)
CC0-1.0
Archived
2026-11-03T10:44:06.039Z
SHA-256 of the archived text
af043acee2e00765e4a2ff4878906bceaff8f7aec7b19c4cc246862f2757afa2
Stable URL of this page
https://metraipolis.com/documento/dc_a657cf746d20

How to cite

RxnMiner: A Multimodal Agent for Structured Reaction Data Extraction from Chemistry Figures — arXiv:2611.02826 — arXiv (en), https://arxiv.org/abs/2611.02826 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a657cf746d20 (Metraipolis archive dc_a657cf746d20, sha256 af043acee2e00765e4a2ff4878906bceaff8f7aec7b19c4cc246862f2757afa2)
BibTeX
@misc{dca657cf746d20,
  title = {RxnMiner: A Multimodal Agent for Structured Reaction Data Extraction from Chemistry Figures — arXiv:2611.02826},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02826},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a657cf746d20; sha256 af043acee2e00765e4a2ff4878906bceaff8f7aec7b19c4cc246862f2757afa2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02826. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reaction data underpin machine learning for reaction prediction, condition recommendation, and retrosynthetic planning, yet extracting these data from literature figures still requires substantial manual effort. Many figures encode multiple experiments through shared templates, substituent tables, and product grids. Recovering concrete reaction records therefore requires molecular recognition, association of evidence with individual experimental entries, and reconstruction of indirectly specified participants. We present RxnMiner, a multimodal agent system that combines an expert-informed extraction procedure with a chemistry toolbox to coordinate these operations. The agent reads molecular structures, resolves shared and entry-specific evidence, and instantiates participants from templates to assemble source-linked reaction records. We also introduce ChemRxn-Bench, a benchmark of 603 reaction figures with 8,547 manually annotated and reviewed reaction records, evaluated under a common protocol for exact molecular identity and reactant-product pairing. On this benchmark, with Qwen3.8-Flash-Next as the backbone, RxnMiner raises stereochemistry-aware reaction macro-F1 from 21.0% under direct prediction to 71.0%, compared with 25.0% for the strongest existing extraction system. Across five backbones, it also outperforms the same base agent without the extraction procedure and chemistry toolbox by 9.4 to 25.5 points. Applied without human intervention to 10,107 literature figures, RxnMiner produces a silver corpus of 88,202 source-linked reaction records.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.02826 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:39:50.314Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).