Paper 2512.02038
Deep Research: A Systematic Survey
- Published
- Nov 2025
- Research lab
- Independent
- Citations
- 15
- GitHub
- 322 stars
01 In brief
Summary
This survey provides a comprehensive overview of Deep Research (DR) systems, which combine large language models with external tools to perform complex, open-ended research tasks.
The authors formalize a three-stage roadmap for DR: Agentic Search, Integrated Research, and Full-stack AI Scientist.
They identify four key components of DR systems: query planning, information acquisition, memory management, and answer generation, each with detailed sub-taxonomies.
The survey also covers practical optimization techniques, including workflow prompting, supervised fine-tuning, and end-to-end reinforcement learning.
It consolidates evaluation benchmarks and discusses open challenges such as retrieval timing, memory evolution, training instability, and evaluation limitations.
The paper aims to guide future development in this rapidly evolving field.
02 From the paper
Abstract
Large language models (LLMs) have rapidly evolved from text generators into powerful problem solvers. Yet, many open tasks demand critical thinking, multi-source, and verifiable outputs, which are beyond single-shot prompting or standard retrieval-augmented generation. Recently, numerous studies have explored Deep Research (DR), which aims to combine the reasoning capabilities of LLMs with external tools, such as search engines, thereby empowering LLMs to act as research agents capable of completing complex, open-ended tasks. This survey presents a comprehensive and systematic overview of deep research systems, including a clear roadmap, foundational components, practical implementation techniques, important challenges, and future directions. Specifically, our main contributions are as follows: (i) we formalize a three-stage roadmap and distinguish deep research from related paradigms; (ii) we introduce four key components: query planning, information acquisition, memory management, and answer generation, each paired with fine-grained sub-taxonomies; (iii) we summarize optimization techniques, including prompting, supervised fine-tuning, and agentic reinforcement learning; and (iv) we consolidate evaluation criteria and open challenges, aiming to guide and facilitate future development. As the field of deep research continues to evolve rapidly, we are committed to continuously updating this survey to reflect the latest progress in this area.