A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
cs.DB, cs.AI
Submitted: 2025-10-27
Updated: 2026-11-16
Comments: Please refer to our paper list and companion materials at: https://github.com/HKUSTDial/awesome-data-agents
Code: https://github.com/HKUSTDial/awesome-data-agents
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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.
Terminology
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. A curated companion repository is available at https://github.com/HKUSTDial/awesome-data-agents.
Sources
- A Survey of LLM $\times$ DATA
- LLM As DBA
- Large Language Models: A Survey
- Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
- AFlow: Automating Agentic Workflow Generation
- ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
- Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems
- Autonomous Data Agents: A New Opportunity for Smart Data
- LLM/Agent-as-Data-Analyst: A Survey
- Large Language Model-based Data Science Agent: A Survey
- GaussMaster: An LLM-based Database Copilot System
- LLM-Based Data Science Agents: A Survey of Capabilities, Challenges, and Future Directions
- Can Large Language Models Be Query Optimizer for Relational Databases?
- E3-Rewrite: Learning to Rewrite SQL for Executability, Equivalence,and Efficiency
- AutoDDG: Automated Dataset Description Generation using Large Language Models
- Evaluating Knowledge Generation and Self-Refinement Strategies for LLM-based Column Type Annotation
- GenRewrite: Query Rewriting via Large Language Models
- Query Rewriting via LLMs
- A Query Optimization Method Utilizing Large Language Models
- Matchmaker: Self-Improving Large Language Model Programs for Schema Matching
Related papers
- Beyond Overlap: Hierarchical Graph Abstraction for Out-of-Core Vector Search
- EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
- Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
- Samyama: A Unified Graph-Vector Database with In-Database Optimization, Agentic Enrichment, and Hardware Acceleration
- GenTUS: Table Union Search via Constrained Generation of Semantic Table Identifiers
- Common-Neighbor-Count-Based Representative Possible World Finding on Uncertain Graphs