arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.09132cs.DBcs.ETcs.MA
收藏

SciDataCopilot: 一种面向AGI驱动科学发现的代理数据准备框架

SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discovery

Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)
Jiyong Rao, Yicheng Qiu, Jiahui Zhang, Juntao Deng, Shangquan Sun, Fenghua Ling, Hao Chen, Nanqing Dong, Zhangyang Gao, Siqi Sun, Yuqiang Li, Dongzhan Zhou, Gua… 展开作者

Jiyong Rao, Yicheng Qiu, Jiahui Zhang, Juntao Deng, Shangquan Sun, Fenghua Ling, Hao Chen, Nanqing Dong, Zhangyang Gao, Siqi Sun, Yuqiang Li, Dongzhan Zhou, Guangyu Wang, Lijun Wu, Conghui He, Xuhong Wang, Jing Shao, Xiang Liu, Yu Zhu, Mianxin Liu, Qihao Zheng, Yinghui Zhang, Jiamin Wu, Xiaosong Wang, Shixiang Tang, Wenlong Zhang, Bo Zhang, Wanli Ouyang, Runkai Zhao, Chunfeng Song, Lei Bai, Chi Zhang

AI总结:

SciDataCopilot通过自主代理框架实现端到端的数据准备,提升科学发现效率与一致性,推动实验驱动的科学通用智能发展。

摘要:

当前人工智能用于科学(AI4S)的现状主要依赖于大规模文本语料库,生成式AI系统在假设生成、文献搜索和多模态推理方面表现出色。然而,加速闭环科学发现的关键瓶颈仍然是原始实验数据的利用。原始数据以极端异质性、高特异性以及深度领域专业知识为特征,既没有与语言表示直接语义对齐,也不具备适合统一嵌入空间的结构同质性。这种脱节阻止了新兴的人工通用智能用于科学(AGI4S)有效对接实验现实。在本工作中,我们扩展了以文本为中心的AI-Ready概念,提出科学AI-Ready数据范式,明确形式化科学数据如何在计算工作流中被指定、结构化和组合。为了实现这一理念,我们提出了SciDataCopilot,一种自主代理框架,旨在以端到端的方式处理数据摄入、科学意图解析和多模态整合。通过将数据准备作为核心操作原语,该框架为可重用、可迁移的系统提供了原则性基础,使向实验驱动的科学通用智能过渡成为可能。在三个异构科学领域中的广泛评估显示,SciDataCopilot在效率、可扩展性和一致性方面优于手动流程,数据准备速度最高可提升30倍。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑