EUVIMEDEUVIMED entdecken
Crossref

Bohrium + SciMaster: Building the infrastructure and ecosystem for agentic science at scale

Linfeng Zhang, Siheng Chen, Yuzhu Cai, Jingyi Chai, Junhan Chang, Kun Chen, Zhi X. Chen, Zhaohan Ding, Yuwen Du, Yuanpeng Gao, Yuan Gao, Jing Gao und 28 weitere

AI Plus · 2026 · 1 (1) · 100005

DOI: 10.59717/ipj.aiplus.2026.100005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI Plus, 2026. Verfasst von Linfeng Zhang und 39 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning, tool use, and verification. Scaling such agentic science remains difficult because workflows are hard to observe and reproduce, many scientific tools and laboratory systems are not agent-ready, and execution traces are often fragmented. We present Bohrium+SciMaster as an infrastructure-and-ecosystem approach to this problem. Bohrium turns scientific data, software, compute, and laboratory systems into governed, traceable, agent-ready capabilities, while SciMaster orchestrates these capabilities into long-horizon scientific workflows. Between them, a scientific intelligence substrate organizes reusable models, knowledge, and components into executable building blocks for workflow reasoning and action. Across eleven representative master agents spanning literature analysis, simulation, optimization, materials design, and experiment-facing workflows, we report deployment-observed reductions in end-to-end scientific cycle time, together with execution-grounded signals from real workloads at multi-million scale. Together, these results point toward Science-as-a-Service: scientific workflows become increasingly executable, observable, and continuously improvable while remaining anchored in traceable validation and human judgment.

Zitieren

APA

Zhang, L., Chen, S., Cai, Y., Chai, J., Chang, J., Chen, K., Chen, Z. X., Ding, Z., Du, Y., Gao, Y., Gao, Y., Gao, J., Gao, Z., Gu, Q., Hong, Y., Huang, Y., Fang, X., Ji, X., Ke, G., …, & Zhang, J. (2026). Bohrium + SciMaster: Building the infrastructure and ecosystem for agentic science at scale. AI Plus, 1(1), 100005. https://doi.org/10.59717/ipj.aiplus.2026.100005

Vancouver

Zhang L, Chen S, Cai Y, Chai J, Chang J, Chen K, et al. Bohrium + SciMaster: Building the infrastructure and ecosystem for agentic science at scale. AI Plus. 2026;1(1):100005. doi:10.59717/ipj.aiplus.2026.100005

BibTeX
@article{Zhang2026,
  author = {Zhang, Linfeng and Chen, Siheng and Cai, Yuzhu and Chai, Jingyi and Chang, Junhan and Chen, Kun and Chen, Zhi X. and Ding, Zhaohan and Du, Yuwen and Gao, Yuanpeng and Gao, Yuan and Gao, Jing and Gao, Zhifeng and Gu, Qiangqiang and Hong, Yanhui and Huang, Yuan and Fang, Xi and Ji, Xiaohong and Ke, Guolin and Lei, Zixing and Li, Xinyu and Li, Yongge and Liao, Ruoxue and Lin, Hang and Lin, Xiaolu and Liu, Fenyi and Liu, Yuxiang and Liu, Xinzijian and Liu, Zexi and Lu, Jintan and Miao, Tingjia and Que, Haohui and Sun, Weijie and Wang, Yanfeng and Wu, Bingyang and Xue, Tianju and Ye, Rui and Zeng, Jinzhe and Zhang, Duo and Zhang, Jiahui},
  title = {Bohrium + SciMaster: Building the infrastructure and ecosystem for agentic science at scale},
  journal = {AI Plus},
  year = {2026},
  volume = {1},
  number = {1},
  pages = {100005},
  doi = {10.59717/ipj.aiplus.2026.100005}
}
Kostenlos starten →