SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discovery
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915788039913472 |
|---|---|
| author | Rao, Jiyong Qiu, Yicheng Zhang, Jiahui Deng, Juntao Sun, Shangquan Ling, Fenghua Chen, Hao Dong, Nanqing Gao, Zhangyang Sun, Siqi Li, Yuqiang Zhou, Dongzhan Wang, Guangyu Wu, Lijun He, Conghui Wang, Xuhong Shao, Jing Liu, Xiang Zhu, Yu Liu, Mianxin Zheng, Qihao Zhang, Yinghui Wu, Jiamin Wang, Xiaosong Tang, Shixiang Zhang, Wenlong Zhang, Bo Ouyang, Wanli Zhao, Runkai Song, Chunfeng Bai, Lei Zhang, Chi |
| author_facet | Rao, Jiyong Qiu, Yicheng Zhang, Jiahui Deng, Juntao Sun, Shangquan Ling, Fenghua Chen, Hao Dong, Nanqing Gao, Zhangyang Sun, Siqi Li, Yuqiang Zhou, Dongzhan Wang, Guangyu Wu, Lijun He, Conghui Wang, Xuhong Shao, Jing Liu, Xiang Zhu, Yu Liu, Mianxin Zheng, Qihao Zhang, Yinghui Wu, Jiamin Wang, Xiaosong Tang, Shixiang Zhang, Wenlong Zhang, Bo Ouyang, Wanli Zhao, Runkai Song, Chunfeng Bai, Lei Zhang, Chi |
| contents | The current landscape of AI for Science (AI4S) is predominantly anchored in large-scale textual corpora, where generative AI systems excel at hypothesis generation, literature search, and multi-modal reasoning. However, a critical bottleneck for accelerating closed-loop scientific discovery remains the utilization of raw experimental data. Characterized by extreme heterogeneity, high specificity, and deep domain expertise requirements, raw data possess neither direct semantic alignment with linguistic representations nor structural homogeneity suitable for a unified embedding space. The disconnect prevents the emerging class of Artificial General Intelligence for Science (AGI4S) from effectively interfacing with the physical reality of experimentation. In this work, we extend the text-centric AI-Ready concept to Scientific AI-Ready data paradigm, explicitly formalizing how scientific data is specified, structured, and composed within a computational workflow. To operationalize this idea, we propose SciDataCopilot, an autonomous agentic framework designed to handle data ingestion, scientific intent parsing, and multi-modal integration in a end-to-end manner. By positioning data readiness as a core operational primitive, the framework provides a principled foundation for reusable, transferable systems, enabling the transition toward experiment-driven scientific general intelligence. Extensive evaluations across three heterogeneous scientific domains show that SciDataCopilot improves efficiency, scalability, and consistency over manual pipelines, with up to 30$\times$ speedup in data preparation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09132 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discovery Rao, Jiyong Qiu, Yicheng Zhang, Jiahui Deng, Juntao Sun, Shangquan Ling, Fenghua Chen, Hao Dong, Nanqing Gao, Zhangyang Sun, Siqi Li, Yuqiang Zhou, Dongzhan Wang, Guangyu Wu, Lijun He, Conghui Wang, Xuhong Shao, Jing Liu, Xiang Zhu, Yu Liu, Mianxin Zheng, Qihao Zhang, Yinghui Wu, Jiamin Wang, Xiaosong Tang, Shixiang Zhang, Wenlong Zhang, Bo Ouyang, Wanli Zhao, Runkai Song, Chunfeng Bai, Lei Zhang, Chi Databases Emerging Technologies Multiagent Systems The current landscape of AI for Science (AI4S) is predominantly anchored in large-scale textual corpora, where generative AI systems excel at hypothesis generation, literature search, and multi-modal reasoning. However, a critical bottleneck for accelerating closed-loop scientific discovery remains the utilization of raw experimental data. Characterized by extreme heterogeneity, high specificity, and deep domain expertise requirements, raw data possess neither direct semantic alignment with linguistic representations nor structural homogeneity suitable for a unified embedding space. The disconnect prevents the emerging class of Artificial General Intelligence for Science (AGI4S) from effectively interfacing with the physical reality of experimentation. In this work, we extend the text-centric AI-Ready concept to Scientific AI-Ready data paradigm, explicitly formalizing how scientific data is specified, structured, and composed within a computational workflow. To operationalize this idea, we propose SciDataCopilot, an autonomous agentic framework designed to handle data ingestion, scientific intent parsing, and multi-modal integration in a end-to-end manner. By positioning data readiness as a core operational primitive, the framework provides a principled foundation for reusable, transferable systems, enabling the transition toward experiment-driven scientific general intelligence. Extensive evaluations across three heterogeneous scientific domains show that SciDataCopilot improves efficiency, scalability, and consistency over manual pipelines, with up to 30$\times$ speedup in data preparation. |
| title | SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discovery |
| topic | Databases Emerging Technologies Multiagent Systems |
| url | https://arxiv.org/abs/2602.09132 |