Deep Research: A Survey of Autonomous Research Agents

TL;DR

This survey reviews the deep research paradigm for autonomous agents that plan, explore, and synthesize web evidence to generate analytical reports, highlighting technical challenges, methods, and future directions.

Contribution

It provides a comprehensive overview of the deep research pipeline, categorizes existing methods, and discusses recent advances and open challenges in developing autonomous research agents.

Findings

Analysis of the four core stages: planning, question developing, web exploration, report generation.

Categorization of key technical challenges and solutions for each stage.

Summary of recent optimization techniques and benchmarks for deep research.

Abstract

The rapid advancement of large language models (LLMs) has driven the development of agentic systems capable of autonomously performing complex tasks. Despite their impressive capabilities, LLMs remain constrained by their internal knowledge boundaries. To overcome these limitations, the paradigm of deep research has been proposed, wherein agents actively engage in planning, retrieval, and synthesis to generate comprehensive and faithful analytical reports grounded in web-based evidence. In this survey, we provide a systematic overview of the deep research pipeline, which comprises four core stages: planning, question developing, web exploration, and report generation. For each stage, we analyze the key technical challenges and categorize representative methods developed to address them. Furthermore, we summarize recent advances in optimization techniques and benchmarks tailored for deep research. Finally, we discuss open challenges and promising research directions, aiming to chart a roadmap toward building more capable and trustworthy deep research agents.