Deep Research: A Survey of Autonomous Research Agents
- URL: http://arxiv.org/abs/2508.12752v1
- Date: Mon, 18 Aug 2025 09:26:14 GMT
- Title: Deep Research: A Survey of Autonomous Research Agents
- Authors: Wenlin Zhang, Xiaopeng Li, Yingyi Zhang, Pengyue Jia, Yichao Wang, Huifeng Guo, Yong Liu, Xiangyu Zhao,
- Abstract summary: The rapid advancement of large language models (LLMs) has driven the development of agentic systems capable of autonomously performing complex tasks.<n>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.<n>We provide a systematic overview of the deep research pipeline, which comprises four core stages: planning, question developing, web exploration, and report generation.
- Score: 33.96146020332329
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research [85.51475655916026]
AgentCPM-Report is a lightweight yet high-performing local solution composed of a framework that mirrors the human writing process.<n>Our framework uses a Writing As Reasoning Policy (WARP), which enables models to dynamically revise outlines.<n>Experiments on DeepResearch Bench, DeepConsult, and DeepResearch Gym demonstrate that AgentCPM-Report outperforms leading closed-source systems.
arXiv Detail & Related papers (2026-02-06T09:45:04Z) - Deep Researcher with Sequential Plan Reflection and Candidates Crossover (Deep Researcher Reflect Evolve) [0.0]
This paper introduces a novel Deep Researcher architecture designed to generate detailed research reports on complex PhD level topics.<n>Our system utilizes two key innovations: Sequential Research Plan Refinement via Reflection and a Candidates Crossover algorithm.<n>Our architecture achieved an overall score of 46.21, demonstrating superior performance by surpassing leading deep research agents.
arXiv Detail & Related papers (2026-01-28T18:45:39Z) - Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey [59.3507264893654]
Issue resolution is a complex Software Engineering task integral to real-world development.<n> benchmarks like SWE-bench revealed this task as profoundly difficult for large language models.<n>This paper presents a systematic survey of this emerging domain.
arXiv Detail & Related papers (2026-01-15T18:55:03Z) - Deep Research: A Systematic Survey [118.82795024422722]
Deep Research (DR) aims to combine the reasoning capabilities of large language models with external tools, such as search engines.<n>This survey presents a comprehensive and systematic overview of deep research systems.
arXiv Detail & Related papers (2025-11-24T15:28:28Z) - WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents [72.28593628378991]
WebResearcher is an iterative deep-research paradigm that reformulates deep research as a Markov Decision Process.<n>WebResearcher achieves state-of-the-art performance, even surpassing frontier proprietary systems.
arXiv Detail & Related papers (2025-09-16T17:57:17Z) - A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges [30.146391942071126]
Large Language Models (LLMs) have revolutionized web search.<n>These agents can comprehend user intentions and environmental context.<n>This survey provides the first systematic analysis of search agents.
arXiv Detail & Related papers (2025-08-03T08:02:51Z) - From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents [96.65646344634524]
Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research.<n>We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn.<n>We demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking.
arXiv Detail & Related papers (2025-06-23T17:27:19Z) - Deep Research Agents: A Systematic Examination And Roadmap [79.04813794804377]
Deep Research (DR) agents are designed to tackle complex, multi-turn informational research tasks.<n>In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute DR agents.
arXiv Detail & Related papers (2025-06-22T16:52:48Z) - DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments [20.498100965239818]
We introduce DeepResearcher, the first comprehensive framework for end-to-end training of LLM-based deep research agents.<n>Unlike RAG-based approaches that assume all necessary information exists within a fixed corpus, our method trains agents to navigate the noisy, unstructured, and dynamic nature of the open web.<n>Extensive experiments on open-domain research tasks demonstrate that DeepResearcher achieves substantial improvements of up to 28.9 points over prompt engineering-based baselines.
arXiv Detail & Related papers (2025-04-04T04:41:28Z) - Enhancing LLM Reasoning with Reward-guided Tree Search [95.06503095273395]
o1-like reasoning approach is challenging, and researchers have been making various attempts to advance this open area of research.<n>We present a preliminary exploration into enhancing the reasoning abilities of LLMs through reward-guided tree search algorithms.
arXiv Detail & Related papers (2024-11-18T16:15:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.