Deep Research: A Survey of Autonomous Research Agents
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913996138872832 |
|---|---|
| author | Zhang, Wenlin Li, Xiaopeng Zhang, Yingyi Jia, Pengyue Wang, Yichao Guo, Huifeng Liu, Yong Zhao, Xiangyu |
| author_facet | Zhang, Wenlin Li, Xiaopeng Zhang, Yingyi Jia, Pengyue Wang, Yichao Guo, Huifeng Liu, Yong Zhao, Xiangyu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12752 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep Research: A Survey of Autonomous Research Agents Zhang, Wenlin Li, Xiaopeng Zhang, Yingyi Jia, Pengyue Wang, Yichao Guo, Huifeng Liu, Yong Zhao, Xiangyu Information Retrieval 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. |
| title | Deep Research: A Survey of Autonomous Research Agents |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2508.12752 |