awesome-data-agents
Continuously updated paper list on advancements in Data Agents. Companion repo to our paper "A Survey of Data Agents: Emerging Paradigm or Overstated Hype?"
What is awesome-data-agents?
Continuously updated paper list on advancements in Data Agents. Companion repo to our paper "A Survey of Data Agents: Emerging Paradigm or Overstated Hype?"
Overview of awesome-data-agents
What it is
This repository is a continuously updated paper list on advancements in Data Agents. It serves as the companion repository to the survey paper “A Survey of Data Agents: Emerging Paradigm or Overstated Hype?”. The repository introduces a hierarchical taxonomy of six levels (L0 to L5) for data agents based on their degree of autonomy, and indexes papers by autonomy level and data-related tasks.
Key features
- Curated paper list on Data Agents, continuously updated.
- Companion repository to the survey paper “A Survey of Data Agents: Emerging Paradigm or Overstated Hype?”.
- Introduces a hierarchical taxonomy of six levels (L0–L5) for data agent autonomy.
- Papers indexed by autonomy level and data-related tasks: Data Management, Data Preparation, and Data Analysis.
- Includes related resources such as benchmarks, surveys, and tutorials.
- Presented a 3-hour tutorial at SIGMOD 2026.
- Launched the KDD Cup 2026 track on Data Agents for Complex Data Analysis.
Use cases
This repository is useful for researchers and practitioners who want to explore the field of data agents, understand the proposed taxonomy, and find categorized papers. It can be used to stay updated on the latest advancements, identify research opportunities, and access related resources such as benchmarks and tutorials.
Getting started
See the repository README for the full paper list and resources.
License and pricing
The license is not stated in the repository. The project is listed as open source.
Based on the project's public README and repository metadata.
