mlsanityData to 7 Oct 2026

Deep Research: A Survey of Autonomous Research Agents

arXiv 2508.12752 ↗First posted 18 Aug 2025cs.IRcited by 63

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

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.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 62 of its 83 references that are in the map. First posted on arXiv 18 Aug 2025.

Builds on

62 of 83 references.

Closest ancestors · 16

Same direction, newest first

  1. 2025Deep Research Agents: A Systematic Examination And Roadmap22 Jun
  2. 2025DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents13 Jun
  3. 2025EvolveSearch: An Iterative Self-Evolving Search Agent28 May
  4. 2025MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability26 May
  5. 2025DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research25 May
  6. 2025ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework23 May
  7. 2025Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning20 May
  8. 2025Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents17 May
  9. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search10 Apr
  10. 2025InSTA: Towards Internet-Scale Training For Agents10 Feb
  11. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  12. 2025Agent Laboratory: Using LLM Agents as Research Assistants8 Jan
4 more
  1. 2024Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents10 Nov
  2. 2024Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems17 Jul
  3. 2024Large Language Models Can Self-Improve At Web Agent Tasks30 May
  4. 2023WebArena: A Realistic Web Environment for Building Autonomous Agents25 Jul

Other references · 46

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  3. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  4. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  5. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  6. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  7. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  8. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 616
  9. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 511
  10. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  11. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 319
  12. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 203
34 more
  1. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskscited by 190
  2. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Spacecited by 141
  3. 2025BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinesecited by 139
  4. 2024Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Datasetcited by 126
  5. 2025MMSearch-R1: Incentivizing LMMs to Searchcited by 120
  6. 2024WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Explorationcited by 100
  7. 2025Acting Less is Reasoning More! Teaching Model to Act Efficientlycited by 80
  8. 2023Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Taskscited by 73
  9. 2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoningcited by 69
  10. 2025VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learningcited by 68
  11. 2024Agent Planning with World Knowledge Modelcited by 66
  12. 2024MindSearch: Mimicking Human Minds Elicits Deep AI Searchercited by 65
  13. 2025AgentRxiv: Towards Collaborative Autonomous Researchcited by 64
  14. 2025DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learningcited by 62
  15. 2025SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesiscited by 55
  16. 2024RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answeringcited by 43
  17. 2025MPO: Boosting LLM Agents with Meta Plan Optimizationcited by 36
  18. 2024Thought of Search: Planning with Language Models Through The Lens of Efficiencycited by 32
  19. 2024Long2RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recallcited by 32
  20. 2025R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learningcited by 32
  21. 2025MedBrowseComp: Benchmarking Medical Deep Research and Computer Usecited by 28
  22. 2024Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraintcited by 27
  23. 2025ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generationcited by 26
  24. 2023Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Promptscited by 23
  25. 2025DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMscited by 21
  26. 2024SFR-RAG: Towards Contextually Faithful LLMscited by 19
  27. 2025Benchmarking LLM Faithfulness in RAG with Evolving Leaderboardscited by 19
  28. 2024Correctness is not Faithfulness in RAG Attributionscited by 18
  29. 2025A Cognitive Writing Perspective for Constrained Long-Form Text Generationcited by 14
  30. 2024WEPO: Web Element Preference Optimization for LLM-based Web Navigationcited by 10
  31. 2024Face4RAG: Factual Consistency Evaluation for Retrieval Augmented Generation in Chinesecited by 9
  32. 2025LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Informationcited by 8
  33. 2025MT-RAIG: Novel Benchmark and Evaluation Framework for Retrieval-Augmented Insight Generation over Multiple Tablescited by 7
  34. 2025DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimizationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 52.

63 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 81
  3. 2025Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analyticscited by 20
  4. 2026MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoningcited by 15
  5. 2025Reinforcement Learning Foundations for Deep Research Systems: A Surveycited by 13
  6. 2025FinDeepResearch: Evaluating Deep Research Agents in Rigorous Financial Analysiscited by 13
  7. 2025DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generationcited by 12
  8. 2026DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivitycited by 11
  9. 2026MemPO: Self-Memory Policy Optimization for Long-Horizon Agentscited by 11
  10. 2026Can We Predict Before Executing Machine Learning Agents?cited by 10
  11. 2026NextMem: Towards Latent Factual Memory for LLM-based Agentscited by 10
  12. 2025Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactionscited by 9
38 more
  1. 2026Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrievalcited by 8
  2. 2026DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agentcited by 8
  3. 2026Search-Time Contamination in Deep Research Agents: Measuring Performance Inflation in Public Benchmark Evaluationcited by 8
  4. 2026Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimizationcited by 7
  5. 2026Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generationcited by 7
  6. 2026DEEPMED: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inferencecited by 6
  7. 2026VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learningcited by 6
  8. 2026On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agentscited by 6
  9. 2026Memory Intelligence Agentcited by 6
  10. 2026TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Explorationcited by 6
  11. 2026Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectorycited by 5
  12. 2026MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcomecited by 5
  13. 2026Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lenscited by 5
  14. 2026What Do Agents Learn from Trajectory-SFT: Semantics or Interfaces?cited by 4
  15. 2026Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Modelscited by 4
  16. 2026DeepInnovator: Triggering the Innovative Capabilities of LLMscited by 4
  17. 2026MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Searchcited by 4
  18. 2026Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysiscited by 4
  19. 2025Dr. Bench: A Multidimensional Evaluation for Deep Research Agents, from Answers to Reportscited by 3
  20. 2026SIGHT: Reinforcement Learning with Self-Evidence and Information-Gain Diverse Branching for Search Agentcited by 3
  21. 2026TVIR: Building Deep Research Agents Towards Text-Visual Interleaved Report Generationcited by 3
  22. 2025Deep Research Agents Brings Deeper Harmcited by 2
  23. 2025Learning a Single Token to Replace Long System Prompts in LLMscited by 2
  24. 2026Unsupervised Skill Discovery for Agentic Data Analysiscited by 2
  25. 2025Structural Enforcement of Statistical Rigor in AI-Driven Discovery: A Functional Architecturecited by 1
  26. 2026Analytical Searchcited by 1
  27. 2026InterDeepResearch: Enabling Human-Agent Collaborative Information Seeking through Interactive Deep Researchcited by 1
  28. 2026APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generationcited by 1
  29. 2026MemoNoveltyAgent: A Historical Research Memory-Aware Agent Workflow for Paper Novelty Assessmentcited by 1
  30. 2026GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflowscited by 1
  31. 2026Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMscited by 1
  32. 2026BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discoverycited by 1
  33. 2026One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attributioncited by 1
  34. 2026FinDeepIndicator: Benchmarking Deep Research Agents in End-to-End Financial Indicator Constructioncited by 1
  35. 2026Cooperation Breakdown in LLM Agents Under Communication Delayscited by 0
  36. 2026BRIDGE: Bridging Reasoning In Distillation Gap Elimination via Structure-Aware Maskingcited by 0
  37. 2026HotelQuEST: Balancing Quality and Efficiency in Agentic Searchcited by 0
  38. 2026SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answeringcited by 0

50 most cited of 63 All 63 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science
  2. 2025Deep Research: A Systematic Survey
  3. 2025A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications
  4. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
  5. 2026IDRBench: Benchmarking the Interactive Capabilities of Deep Research Agents
  6. 2025Deep Research Bench: Evaluating AI Web Research Agents
  7. 2025Rethinking the Design of Reinforcement Learning-Based Deep Research Agents
  8. 2025ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents