让AI自主完成深度研究，从规划到报告全链路自动化。
Deep Research: A Survey of Autonomous Research Agents
- 构建四阶段流程：规划、提问、网页探索、报告生成
- 突破LLM知识边界，依赖网络证据生成可信分析
- 适合需要自动调研与报告的科研或决策场景
大语言模型（LLMs）的快速发展推动了能够自主执行复杂任务的智能体系统的发展。尽管能力出众，LLMs仍受限于其内部知识范围。为克服这一局限，提出了深度研究范式，即智能体主动进行规划、检索与综合，基于网络证据生成全面且可靠的分析报告。本文系统综述深度研究全流程，包含四个核心阶段：规划、问题构建、网络探索与报告生成。针对每个阶段，分析关键技术挑战并分类代表性方法。此外，总结近期优化技术与专用基准测试进展。最后，讨论开放性挑战与有前景的研究方向，旨在为构建更强大、可信的深度研究智能体提供路线图。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。