A Survey of Data Agents: Emerging Paradigm or Overstated Hype?

TL;DR

This survey introduces a hierarchical taxonomy for data agents, clarifies their capabilities, and reviews research progress from manual to fully autonomous systems, highlighting technical gaps and future directions.

Contribution

It provides the first systematic taxonomy for data agents, clarifies terminology, and offers a structured review of research across different autonomy levels.

Findings

Established a six-level hierarchy for data agent autonomy.

Reviewed existing research aligned with the autonomy levels.

Identified key technical gaps and future research directions.

Abstract

The rapid advancement of large language models (LLMs) has spurred the emergence of data agents, autonomous systems designed to orchestrate Data + AI ecosystems for tackling complex data-related tasks. However, the term "data agent" currently suffers from terminological ambiguity and inconsistent adoption, conflating simple query responders with sophisticated autonomous architectures. This terminological ambiguity fosters mismatched user expectations, accountability challenges, and barriers to industry growth. Inspired by the SAE J3016 standard for driving automation, this survey introduces the first systematic hierarchical taxonomy for data agents, comprising six levels that delineate and trace progressive shifts in autonomy, from manual operations (L0) to a vision of generative, fully autonomous data agents (L5), thereby clarifying capability boundaries and responsibility allocation. Through this lens, we offer a structured review of existing research arranged by increasing autonomy, encompassing specialized data agents for data management, preparation, and analysis, alongside emerging efforts toward versatile, comprehensive systems with enhanced autonomy. We further analyze critical evolutionary leaps and technical gaps for advancing data agents, especially the ongoing L2-to-L3 transition, where data agents evolve from procedural execution to autonomous orchestration. Finally, we conclude with a forward-looking roadmap, envisioning proactive, generative data agents.