SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discovery
🤖 AI Summary
Scientific experimental data remain underutilized by general-purpose AI systems due to their high heterogeneity, domain specificity, and lack of semantic alignment, thereby impeding closed-loop scientific discovery. This work proposes the “AI-Ready Scientific Data” paradigm, extending the concept of AI-readiness from text to multimodal scientific data for the first time. It formally defines the specifications, structure, and compositional principles of such data and introduces SciDataCopilot, an autonomous agent framework that end-to-end interprets scientific intent, fuses multimodal data, and automates data preparation. Evaluations across three heterogeneous scientific domains demonstrate up to a 30-fold efficiency gain over manual workflows, significantly enhancing reusability, transferability, and consistency, thus establishing a foundational data interface for AGI-driven scientific research.
Application Category
📝 Abstract
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.
Problem
Research questions and friction points this paper is trying to address.
raw experimental data
heterogeneity
semantic alignment
AGI4S
data readiness
Innovation
Methods, ideas, or system contributions that make the work stand out.
AI-Ready data
agentic framework
scientific data preparation
Artificial General Intelligence for Science
data readiness
🔎 Similar Papers
No similar papers found.
