Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yuyu Luo, Guoliang Li, Ju Fan, Nan Tang

TL;DR

This paper proposes a hierarchical L0–L5 taxonomy for data agents to resolve terminology ambiguity and clarify autonomy, responsibility, and governance within Data+AI ecosystems. It situates data agents along the data lifecycle—data management, data preparation, and data analysis—distinguishing them from general LLM agents and reviewing representative L0–L2 systems as well as proto-L3 research and industrial offerings. The discussion identifies bottlenecks preventing full L3 autonomy and presents a roadmap toward L4 proactive autonomous data agents and L5 generative data agents, emphasizing perception, planning, governance, safety, and evaluation. By outlining concrete opportunities and challenges, the framework aims to guide researchers, developers, and regulators in calibrating expectations and shaping the next decade of data-agent development.

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.

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

TL;DR

This paper proposes a hierarchical L0–L5 taxonomy for data agents to resolve terminology ambiguity and clarify autonomy, responsibility, and governance within Data+AI ecosystems. It situates data agents along the data lifecycle—data management, data preparation, and data analysis—distinguishing them from general LLM agents and reviewing representative L0–L2 systems as well as proto-L3 research and industrial offerings. The discussion identifies bottlenecks preventing full L3 autonomy and presents a roadmap toward L4 proactive autonomous data agents and L5 generative data agents, emphasizing perception, planning, governance, safety, and evaluation. By outlining concrete opportunities and challenges, the framework aims to guide researchers, developers, and regulators in calibrating expectations and shaping the next decade of data-agent development.

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.
Paper Structure (30 sections, 1 equation, 3 figures, 2 tables)

This paper contains 30 sections, 1 equation, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Tutorial Overview
  3. Our Scope and Goals
  4. Tutorial Outline
  5. Background and Problem Definition
  6. Problem Description: What is a Data Agent?
  7. Task Landscape and Data Agents vs. General LLM Agents
  8. Key Challenges
  9. The L0--L5 Hierarchy of Data Agents
  10. Levels of Autonomy
  11. L0: No Autonomy.
  12. L1: Assistance.
  13. L2: Partial Autonomy.
  14. L3: Conditional Autonomy.
  15. L4: High Autonomy.
  16. ...and 15 more sections

Figures (3)

  • Figure 1: An Overview of Data Agents. (https://github.com/HKUSTDial/awesome-data-agents)
  • Figure 2: Representative Data Agents Across Different Levels.
  • Figure 3: L3 Data Agents (Conditional Autonomy).