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.

翻译：大语言模型（LLMs）已从文本生成器迅速发展为强大的问题求解器。然而，许多开放任务需要批判性思维、多源信息及可验证的输出，这超出了单次提示或标准检索增强生成的能力范围。近期，众多研究探索了深度研究（DR），其目标是将LLMs的推理能力与外部工具（如搜索引擎）相结合，从而使LLMs能够作为研究代理完成复杂、开放式的任务。本综述对深度研究系统进行了全面且系统的概述，包括清晰的路线图、基础组件、实际实现技术、重要挑战及未来方向。具体而言，我们的主要贡献如下：（i）形式化了一个三阶段路线图，并将深度研究与相关范式区分开来；（ii）介绍了四个关键组件：查询规划、信息获取、记忆管理和答案生成，每个组件均配有细粒度的子分类；（iii）总结了优化技术，包括提示工程、监督微调和智能体强化学习；（iv）整合了评估标准和开放挑战，旨在指导和促进未来发展。随着深度研究领域的持续快速发展，我们致力于不断更新本综述，以反映该领域的最新进展。