Deep Research: A Systematic Survey
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.
Authors 21
-
Affiliation as printed
Renmin University of China
-
Affiliation as printed
Tsinghua University
-
Affiliation as printed
Carnegie Mellon University
-
Affiliation as printed
University of Amsterdam
-
University of Massachusetts Amherst
Affiliation as printed
University of Massachusetts Amherst
-
University of Illinois Urbana-Champaign
Affiliation as printed
University of Illinois Urbana-Champaign
-
Affiliation as printed
Westlake University
-
Affiliation as printed
Westlake University
-
Affiliation as printed
Westlake University
-
Affiliation as printed
University of Arizona
-
Qu Yang Aachen
Affiliation as printed
Tencent 12 Leiden University
-
Jiang Wu Aachen
Affiliation as printed
Tencent 12 Leiden University
-
Xiaqiang Tang Aachen
Affiliation as printed
Tencent 12 Leiden University
-
Xin Ma Aachen
Affiliation as printed
Tencent 12 Leiden University
-
Affiliation as printed
Tsinghua University
-
Affiliation as printed
Tsinghua University
-
Affiliation as printed
Renmin University of China
-
Affiliation as printed
Westlake University
-
Affiliation as printed
Carnegie Mellon University
-
Affiliation as printed
Tencent 12 Leiden University
-
Zhaochun Ren corresponding
Cited by 1 stored of 1
1 result
No patents citing this paper on Lens.org (checked 2026-10-11).