From Raw Scientific Data to Trusted Discovery: Agentic AI for FAIR and Reproducible Data Science: A Systematic Review of Data Engineering, Semantic Data Models, Multimodal Analytics, Provenance, and Human Oversight
Sep 2026· Scholars Journal of Engineering and Technology· 0 citations
TL;DR
The review concludes with a staged research agenda and an integrated framework that links FAIR practice, reproducibility engineering, and human governance across the scientific lifecycle.
Abstract
Agentic artificial intelligence (AI) is beginning to change scientific data work from a sequence of manually connected tasks into a set of tool-mediated, partially autonomous workflows. That shift creates a practical question: can agents accelerate analysis without weakening the findability, accessibility, interoperability, reusability (FAIR), and reproducibility on which scientific claims depend? We systematically reviewed 218 peer-reviewed papers, preprints, and community standards published from 2016 to September 2026. The evidence was organized into five linked domains: data engineering and AutoML; semantic data models and knowledge graphs; multimodal analytics and retrieval-augmented generation; provenance and reproducibility; and human oversight, trust, and governance. Across these domains, the literature shows clear progress in execution-grounded data preparation, workflow orchestration, semantic retrieval, and multimodal evidence synthesis. It also shows a consistent boundary: systems can generate plausible analyses faster than they can establish that those analyses are complete, reproducible, and scientifically warranted. The most persistent weaknesses are incomplete lineage, unstable dependencies, weak cross-modal semantics, inconsistent evaluation, and poorly calibrated human reliance. We therefore frame trustworthy agentic science as a data-to-decision problem rather than a model-selection problem. Agents should produce claim-level provenance, machine-actionable semantic metadata, executable environments, uncertainty-aware outputs, and explicit escalation points for human review. The review concludes with a staged research agenda and an integrated framework that links FAIR practice, reproducibility engineering, and human governance across the scientific lifecycle.
Results indicate that SciDSK improves how agents locate and understand scientific datasets, providing a stronger foundation for actionable scientific data use.
Xiao-Han Huang, Qing-Qing Long, Xiaolei Du et al.· 0 citations
A conceptual framework for Agentic Data Engineering centered on Quality of Agentic Data Use, defined as the extent to which an agent uses and communicates data in accordance with task, semantic, quality, security, governance, and provenance requirements, is developed.
A. Cravero, Jorge Díaz-Villegas, Zi-Hao Xiao· Applied Sciences· 0 citations
This paper examines Data Agents from a harness-centric perspective, introducing a taxonomy of Data Agents and associated data environments, and identifying four open reliability problems: inactive semantic calibration, missing clarification, missing experience transfer, and the missing verification-repair repository.
Hua-Chi Zhou, Yu-Jing Zhang, Jia-He Du et al.· 0 citations
Agentic artificial intelligence is transforming enterprise metadata management from rule-based automation to goal-directed systems capable of discovering, interpreting, connecting, and governing metadata across heterogeneous data estates. This review evaluates how autonomous agents can facilitate metadata discovery, se...
Uzair Momin· Global academic journal of e...· 0 citations
The design of a workflow blueprint compliant with FAIR principles and grounded in Open Science practices, developed for the retrieval, harmonisation, and publication of curated bibliographic metadata is introduced.
Arianna Moretti, Iiro Tiihonen, Jonas Fischer· 0 citations
. Search engine optimization (SEO) workflows remain difficult to auto-mate and integrate because they span heterogeneous tools while relying on loosely structured data models that provide limited machine-interpretable representations of content, actions, and performance signals. This fragmentation hinders interoperabilit...
Emilija Gjorgjevska, David Riccitelli, Milos Jovanovik et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.