Large Language Model-based Data Science Agent: A Survey

TL;DR

This survey reviews recent developments in Large Language Model-based agents for data science, highlighting design principles and practical workflows, and offers a dual-framework connecting agent design with data science tasks.

Contribution

It provides a comprehensive review of LLM-based data science agents and introduces a dual-perspective framework linking agent design principles with data science workflows.

Findings

Summarizes recent advances in LLM-based data science agents

Identifies key design principles and processes for these agents

Proposes a dual-framework connecting agent design with data science workflows

Abstract

The rapid advancement of Large Language Models (LLMs) has driven novel applications across diverse domains, with LLM-based agents emerging as a crucial area of exploration. This survey presents a comprehensive analysis of LLM-based agents designed for data science tasks, summarizing insights from recent studies. From the agent perspective, we discuss the key design principles, covering agent roles, execution, knowledge, and reflection methods. From the data science perspective, we identify key processes for LLM-based agents, including data preprocessing, model development, evaluation, visualization, etc. Our work offers two key contributions: (1) a comprehensive review of recent developments in applying LLMbased agents to data science tasks; (2) a dual-perspective framework that connects general agent design principles with the practical workflows in data science.