跳到正文
arXiv cs.AI· Yufan Chen, Ching Ting Leung, Bowen Yu, Haifan Zhou, Jianwei Sun, Yong Huang, Linyan Li, Hao Chen, Hanyu Gao·· 2 小时前AI 评分51

ChemEAGLE 多智能体系统从化学文献大规模构建可验证反应数据库

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

AI 导读

研究者提出多智能体系统 ChemEAGLE,由工具提供分子结构、语言模型做判断,从文献图形大规模构建可验证化学反应数据库。在 424 个已发表图形上,完全正确反应的 F1 为 82.2%,高于配备工具的通用智能体的 47.7%;经校准置信度筛选后仅需人工复核 35% 的反应,准确率达 96.6%。

正文 · 原文

View PDF HTML (experimental)

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.
Comments: v4: substantially revised; new title, one added author. Adds a expanded 424-graphic benchmark, generalist-agent baselines, calibrated confidence scores, and downstream tasks: condition ranking and product prediction trained on a 60,103-reaction photochemistry database. Results in v1-v3 are superseded. 92 pages, 5 figures
Subjects: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Multiagent Systems (cs.MA)
Cite as: arXiv:2507.20230 [cs.AI]
  (or arXiv:2507.20230v4 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2507.20230

arXiv-issued DOI via DataCite

Submission history

From: Yufan Chen [view email]
[v1] Sun, 27 Jul 2025 11:16:57 UTC (7,650 KB)
[v2] Tue, 29 Jul 2025 02:55:37 UTC (7,107 KB)
[v3] Fri, 6 Mar 2026 11:15:48 UTC (12,212 KB)
[v4] Tue, 17 Nov 2026 10:00:34 UTC (6,338 KB)

来源:arXiv cs.AI · arxiv.org