Deep Research: A Systematic Survey
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908686361821184 |
|---|---|
| author | Shi, Zhengliang Chen, Yiqun Li, Haitao Sun, Weiwei Ni, Shiyu Lyu, Yougang Fan, Run-Ze Jin, Bowen Weng, Yixuan Zhu, Minjun Xie, Qiujie Guo, Xinyu Yang, Qu Wu, Jiayi Zhao, Jujia Tang, Xiaqiang Ma, Xinbei Wang, Cunxiang Mao, Jiaxin Ai, Qingyao Huang, Jen-Tse Wang, Wenxuan Zhang, Yue Yang, Yiming Tu, Zhaopeng Ren, Zhaochun |
| author_facet | Shi, Zhengliang Chen, Yiqun Li, Haitao Sun, Weiwei Ni, Shiyu Lyu, Yougang Fan, Run-Ze Jin, Bowen Weng, Yixuan Zhu, Minjun Xie, Qiujie Guo, Xinyu Yang, Qu Wu, Jiayi Zhao, Jujia Tang, Xiaqiang Ma, Xinbei Wang, Cunxiang Mao, Jiaxin Ai, Qingyao Huang, Jen-Tse Wang, Wenxuan Zhang, Yue Yang, Yiming Tu, Zhaopeng Ren, Zhaochun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02038 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep Research: A Systematic Survey Shi, Zhengliang Chen, Yiqun Li, Haitao Sun, Weiwei Ni, Shiyu Lyu, Yougang Fan, Run-Ze Jin, Bowen Weng, Yixuan Zhu, Minjun Xie, Qiujie Guo, Xinyu Yang, Qu Wu, Jiayi Zhao, Jujia Tang, Xiaqiang Ma, Xinbei Wang, Cunxiang Mao, Jiaxin Ai, Qingyao Huang, Jen-Tse Wang, Wenxuan Zhang, Yue Yang, Yiming Tu, Zhaopeng Ren, Zhaochun Computation and Language Artificial Intelligence Information Retrieval 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. |
| title | Deep Research: A Systematic Survey |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2512.02038 |