Data Agents: Levels, State of the Art, and Open Problems

2026-02-04

AI Summary

This study addresses the ambiguity surrounding the concept of “data agents” and the absence of a unified capability taxonomy, which hinders clear delineation of their operational boundaries and accountability. To resolve this, we propose the first six-tier hierarchical classification framework, spanning from Level 0 (no autonomy) to Level 5 (full autonomy), explicitly defining the critical transition characteristics at each tier. Building upon this structure, we develop a lifecycle- and level-driven analytical framework, conduct a systematic review of existing technologies, and introduce a Proto-Level 3 system paradigm tailored for end-to-end data workflows. Furthermore, we outline forward-looking research pathways toward Levels 4 and 5. Our work establishes a theoretical foundation, provides a practical roadmap, and charts a decade-long research agenda for the design, evaluation, and governance of data agents.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Modeling other Agents
• Knowledge Representation and Reasoning: Ontologies

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Security and Privacy: Data transparency and provenance
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

Data agents are an emerging paradigm that leverages large language models (LLMs) and tool-using agents to automate data management, preparation, and analysis tasks. However, the term"data agent"is currently used inconsistently, conflating simple query responsive assistants with aspirational fully autonomous"data scientists". This ambiguity blurs capability boundaries and accountability, making it difficult for users, system builders, and regulators to reason about what a"data agent"can and cannot do. In this tutorial, we propose the first hierarchical taxonomy of data agents from Level 0 (L0, no autonomy) to Level 5 (L5, full autonomy). Building on this taxonomy, we will introduce a lifecycleand level-driven view of data agents. We will (1) present the L0-L5 taxonomy and the key evolutionary leaps that separate simple assistants from truly autonomous data agents, (2) review representative L0-L2 systems across data management, preparation, and analysis, (3) highlight emerging Proto-L3 systems that strive to autonomously orchestrate end-to-end data workflows to tackle diverse and comprehensive data-related tasks under supervision, and (4) discuss forward-looking research challenges towards proactive (L4) and generative (L5) data agents. We aim to offer both a practical map of today's systems and a research roadmap for the next decade of data-agent development.

Problem

• data agents
• autonomy
• taxonomy
• capability boundaries
• accountability

Innovation

• data agents
• autonomy levels
• LLM-powered agents
• taxonomy
• data workflow automation