AgenticData: An Agentic Data Analytics System for Heterogeneous Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Ji, Li, Guoliang, Zhou, Peiyao, Ma, Yihui, Xu, Jingzhe, Li, Yuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913978798571520
author Sun, Ji
Li, Guoliang
Zhou, Peiyao
Ma, Yihui
Xu, Jingzhe
Li, Yuan
author_facet Sun, Ji
Li, Guoliang
Zhou, Peiyao
Ma, Yihui
Xu, Jingzhe
Li, Yuan
contents Existing unstructured data analytics systems rely on experts to write code and manage complex analysis workflows, making them both expensive and time-consuming. To address these challenges, we introduce AgenticData, an innovative agentic data analytics system that allows users to simply pose natural language (NL) questions while autonomously analyzing data sources across multiple domains, including both unstructured and structured data. First, AgenticData employs a feedback-driven planning technique that automatically converts an NL query into a semantic plan composed of relational and semantic operators. We propose a multi-agent collaboration strategy by utilizing a data profiling agent for discovering relevant data, a semantic cross-validation agent for iterative optimization based on feedback, and a smart memory agent for maintaining short-term context and long-term knowledge. Second, we propose a semantic optimization model to refine and execute semantic plans effectively. Our system, AgenticData, has been tested using three benchmarks. Experimental results showed that AgenticData achieved superior accuracy on both easy and difficult tasks, significantly outperforming state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05002
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AgenticData: An Agentic Data Analytics System for Heterogeneous Data
Sun, Ji
Li, Guoliang
Zhou, Peiyao
Ma, Yihui
Xu, Jingzhe
Li, Yuan
Databases
Artificial Intelligence
Existing unstructured data analytics systems rely on experts to write code and manage complex analysis workflows, making them both expensive and time-consuming. To address these challenges, we introduce AgenticData, an innovative agentic data analytics system that allows users to simply pose natural language (NL) questions while autonomously analyzing data sources across multiple domains, including both unstructured and structured data. First, AgenticData employs a feedback-driven planning technique that automatically converts an NL query into a semantic plan composed of relational and semantic operators. We propose a multi-agent collaboration strategy by utilizing a data profiling agent for discovering relevant data, a semantic cross-validation agent for iterative optimization based on feedback, and a smart memory agent for maintaining short-term context and long-term knowledge. Second, we propose a semantic optimization model to refine and execute semantic plans effectively. Our system, AgenticData, has been tested using three benchmarks. Experimental results showed that AgenticData achieved superior accuracy on both easy and difficult tasks, significantly outperforming state-of-the-art methods.
title AgenticData: An Agentic Data Analytics System for Heterogeneous Data
topic Databases
Artificial Intelligence
url https://arxiv.org/abs/2508.05002