A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

TL;DR

This survey reviews the development, architecture, optimization, and evaluation of LLM-based deep search agents, highlighting their potential, challenges, and future research directions in autonomous information seeking.

Contribution

It provides the first comprehensive systematic analysis and categorization of existing LLM-based search agents, outlining key open challenges and future research avenues.

Findings

Categorized existing works by architecture, optimization, application, and evaluation.

Identified critical open challenges in LLM-based search agents.

Outlined promising future research directions.

Abstract

The advent of Large Language Models (LLMs) has significantly revolutionized web search. The emergence of LLM-based Search Agents marks a pivotal shift towards deeper, dynamic, autonomous information seeking. These agents can comprehend user intentions and environmental context and execute multi-turn retrieval with dynamic planning, extending search capabilities far beyond the web. Leading examples like OpenAI's Deep Research highlight their potential for deep information mining and real-world applications. This survey provides the first systematic analysis of search agents. We comprehensively analyze and categorize existing works from the perspectives of architecture, optimization, application, and evaluation, ultimately identifying critical open challenges and outlining promising future research directions in this rapidly evolving field. Our repository is available on https://github.com/YunjiaXi/Awesome-Search-Agent-Papers.