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

TL;DR

SciDataCopilot introduces an autonomous framework that enhances data preparation for scientific discovery, significantly improving efficiency and scalability in handling heterogeneous experimental data for AGI-driven research.

Contribution

The paper formalizes a scientific data paradigm and develops SciDataCopilot, an agentic system for end-to-end data ingestion, parsing, and integration in scientific workflows.

Findings

Up to 30x speedup in data preparation tasks.

Improved efficiency, scalability, and consistency over manual pipelines.

Validated across three diverse scientific domains.

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.