Skip to content

Data Agents: Rethinking Data Systems in the AI Agent Era

Aug 2026 · Proceedings of the VLDB Endowment · Vol 19, pp. 4946-4949 · 0 citations · 19 references

TL;DR

This panel will convene leading researchers and practitioners to discuss the future of data agents, which is defined as an autonomous system capable of perceiving data in various forms, planning and executing complex data manipulation and analysis tasks, and interacting with humans through natural language or other intuitive interfaces.

Abstract

The database community is at a pivotal moment. Large Language Models (LLMs) and AI agents are rapidly changing how users interact with data systems. The traditional model—where human experts write SQL queries or navigate complex BI tools—is being disrupted by a new vision: data agents capable of understanding natural language, reasoning about data semantics, autonomously executing multi-step analytical workflows, and collaborating with humans to derive insights. This shift introduces fundamental questions that span database systems, human-computer interaction, AI/ML infrastructure, and programming languages. This panel will convene leading researchers and practitioners to discuss the future of data agents. A "data agent" is defined as an autonomous system capable of perceiving data in various forms (structured, semi-structured, and unstructured), planning and executing complex data manipulation and analysis tasks, interacting with humans through natural language or other intuitive interfaces, and learning from feedback to improve over time. The panel will examine whether this vision is achievable, the technical obstacles that need to be addressed, and how the database community should adapt to meet this emerging challenge.

View source

Similar papers

#artificial intelligence Open access Sep 2026

Data Agents: Agentic Data Systems

This work proposes a new paradigm called the Data Agent, designed to manage, process, and analyze data with minimal human intervention, and develops two specialized agents: the data analytics agent and the data science agent.

Guo-Liang Li, Pei-Yao Zhou, Xuan-He Zhou et al. · 0 citations
Review Aug 2026

MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systems

MUSE is presented, an interactive meta-agent that enhances user understanding and control of agentic data science systems by dynamically restructuring low-level execution traces into multiple semantic levels that support navigation from high-level overviews to low-level implementation details.

Wei-Hao Chen, Weixi Tong, Yuan Tian et al. · 0 citations

RUBICON: Agentic AI for Messy Enterprise Data

This work argues that text-to-SQL fails on real enterprise data and must be dramatically subsetted to achieve reliable results, and introduces RUBICON, a system that embodies this vision and surpasses both LOTUS and Palimpzest on a semantic query benchmark.

Unknown authors · 0 citations

AgenticData : An Agentic Data System on Heterogeneous Data

The AgenticData system, an agentic data system that enables natural-language query analytics over heterogeneous data sources, is introduced and its ability to handle diverse data sources accurately and efficiently is illustrated.

Pei-Yao Zhou, Ji Sun, Yao-Qiang Xu et al. · 0 citations
#artificial intelligence Preprint Aug 2026

CrabOS: An Operating System for Human-AI Co-inhabitation

CrabOS elevates support for complex tasks with alternating human and AI leadership from bridge-dependent application-level solutions to native operating-system capabilities, which provide a new foundation for developing and running AI agents.

Qi Yang, Yun Ma · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.