Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.20469 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912785985699840 |
|---|---|
| author | Zhang, Linfeng Chen, Siheng Cai, Yuzhu Chai, Jingyi Chang, Junhan Chen, Kun Chen, Zhi X. Ding, Zhaohan Du, Yuwen Gao, Yuanpeng Gao, Yuan Gao, Jing Gao, Zhifeng Gu, Qiangqiang Hong, Yanhui Huang, Yuan Fang, Xi Ji, Xiaohong Ke, Guolin Lei, Zixing Li, Xinyu Li, Yongge Liao, Ruoxue Lin, Hang Lin, Xiaolu Liu, Yuxiang Liu, Xinzijian Liu, Zexi Lu, Jintan Miao, Tingjia Que, Haohui Sun, Weijie Wang, Yanfeng Wu, Bingyang Xue, Tianju Ye, Rui Zeng, Jinzhe Zhang, Duo Zhang, Jiahui Zhang, Linfeng Zhang, Tianhan Zhang, Wenchang Zhang, Yuzhi Zhang, Zezhong Zheng, Hang Zhou, Hui Zhu, Tong Zhu, Xinyu Zhou, Qingguo E, Weinan |
| author_facet | Zhang, Linfeng Chen, Siheng Cai, Yuzhu Chai, Jingyi Chang, Junhan Chen, Kun Chen, Zhi X. Ding, Zhaohan Du, Yuwen Gao, Yuanpeng Gao, Yuan Gao, Jing Gao, Zhifeng Gu, Qiangqiang Hong, Yanhui Huang, Yuan Fang, Xi Ji, Xiaohong Ke, Guolin Lei, Zixing Li, Xinyu Li, Yongge Liao, Ruoxue Lin, Hang Lin, Xiaolu Liu, Yuxiang Liu, Xinzijian Liu, Zexi Lu, Jintan Miao, Tingjia Que, Haohui Sun, Weijie Wang, Yanfeng Wu, Bingyang Xue, Tianju Ye, Rui Zeng, Jinzhe Zhang, Duo Zhang, Jiahui Zhang, Linfeng Zhang, Tianhan Zhang, Wenchang Zhang, Yuzhi Zhang, Zezhong Zheng, Hang Zhou, Hui Zhu, Tong Zhu, Xinyu Zhou, Qingguo E, Weinan |
| contents | AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning with tool use and verification, pointing to a shift from isolated AI-assisted steps toward \emph{agentic science at scale}. This shift is increasingly feasible, as scientific tools and models can be invoked through stable interfaces and verified with recorded execution traces, and increasingly necessary, as AI accelerates scientific output and stresses the peer-review and publication pipeline, raising the bar for traceability and credible evaluation.
However, scaling agentic science remains difficult: workflows are hard to observe and reproduce; many tools and laboratory systems are not agent-ready; execution is hard to trace and govern; and prototype AI Scientist systems are often bespoke, limiting reuse and systematic improvement from real workflow signals.
We argue that scaling agentic science requires an infrastructure-and-ecosystem approach, instantiated in Bohrium+SciMaster. Bohrium acts as a managed, traceable hub for AI4S assets -- akin to a HuggingFace of AI for Science -- that turns diverse scientific data, software, compute, and laboratory systems into agent-ready capabilities. SciMaster orchestrates these capabilities into long-horizon scientific workflows, on which scientific agents can be composed and executed. Between infrastructure and orchestration, a \emph{scientific intelligence substrate} organizes reusable models, knowledge, and components into executable building blocks for workflow reasoning and action, enabling composition, auditability, and improvement through use.
We demonstrate this stack with eleven representative master agents in real workflows, achieving orders-of-magnitude reductions in end-to-end scientific cycle time and generating execution-grounded signals from real workloads at multi-million scale. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_20469 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale Zhang, Linfeng Chen, Siheng Cai, Yuzhu Chai, Jingyi Chang, Junhan Chen, Kun Chen, Zhi X. Ding, Zhaohan Du, Yuwen Gao, Yuanpeng Gao, Yuan Gao, Jing Gao, Zhifeng Gu, Qiangqiang Hong, Yanhui Huang, Yuan Fang, Xi Ji, Xiaohong Ke, Guolin Lei, Zixing Li, Xinyu Li, Yongge Liao, Ruoxue Lin, Hang Lin, Xiaolu Liu, Yuxiang Liu, Xinzijian Liu, Zexi Lu, Jintan Miao, Tingjia Que, Haohui Sun, Weijie Wang, Yanfeng Wu, Bingyang Xue, Tianju Ye, Rui Zeng, Jinzhe Zhang, Duo Zhang, Jiahui Zhang, Linfeng Zhang, Tianhan Zhang, Wenchang Zhang, Yuzhi Zhang, Zezhong Zheng, Hang Zhou, Hui Zhu, Tong Zhu, Xinyu Zhou, Qingguo E, Weinan Artificial Intelligence AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning with tool use and verification, pointing to a shift from isolated AI-assisted steps toward \emph{agentic science at scale}. This shift is increasingly feasible, as scientific tools and models can be invoked through stable interfaces and verified with recorded execution traces, and increasingly necessary, as AI accelerates scientific output and stresses the peer-review and publication pipeline, raising the bar for traceability and credible evaluation. However, scaling agentic science remains difficult: workflows are hard to observe and reproduce; many tools and laboratory systems are not agent-ready; execution is hard to trace and govern; and prototype AI Scientist systems are often bespoke, limiting reuse and systematic improvement from real workflow signals. We argue that scaling agentic science requires an infrastructure-and-ecosystem approach, instantiated in Bohrium+SciMaster. Bohrium acts as a managed, traceable hub for AI4S assets -- akin to a HuggingFace of AI for Science -- that turns diverse scientific data, software, compute, and laboratory systems into agent-ready capabilities. SciMaster orchestrates these capabilities into long-horizon scientific workflows, on which scientific agents can be composed and executed. Between infrastructure and orchestration, a \emph{scientific intelligence substrate} organizes reusable models, knowledge, and components into executable building blocks for workflow reasoning and action, enabling composition, auditability, and improvement through use. We demonstrate this stack with eleven representative master agents in real workflows, achieving orders-of-magnitude reductions in end-to-end scientific cycle time and generating execution-grounded signals from real workloads at multi-million scale. |
| title | Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2512.20469 |