mlsanityData to 14 Oct 2026

A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

arXiv 2508.05668 ↗First posted 3 Aug 2025cs.IR cs.AI cs.CLcited by 62

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

Abstract (arXiv)

The advent of Large Language Models (LLMs) has significantly revolutionized web search. The emergence of LLM-based Search Agents marks a pivotal shift towards deeper, dynamic, autonomous information seeking. These agents can comprehend user intentions and environmental context and execute multi-turn retrieval with dynamic planning, extending search capabilities far beyond the web. Leading examples like OpenAI's Deep Research highlight their potential for deep information mining and real-world applications. This survey provides the first systematic analysis of search agents. We comprehensively analyze and categorize existing works from the perspectives of architecture, optimization, application, and evaluation, ultimately identifying critical open challenges and outlining promising future research directions in this rapidly evolving field. Our repository is available on https://github.com/YunjiaXi/Awesome-Search-Agent-Papers.

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 138 of its 195 references that are in the map. First posted on arXiv 3 Aug 2025.

Builds on

138 of 195 references.

Closest ancestors · 21

Same direction, newest first

  1. 2025Deep Research Comparator: A Platform For Fine-grained Human Annotations of Deep Research Agents7 Jul
  2. 2025WebSailor: Navigating Super-human Reasoning for Web Agent3 Jul
  3. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents23 Jun
  4. 2025Deep Research Agents: A Systematic Examination And Roadmap22 Jun
  5. 2025DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents13 Jun
  6. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges12 Jun
  7. 2025MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability26 May
  8. 2025Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers26 May
  9. 2025MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning26 May
  10. 2025ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework23 May
  11. 2025Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty22 May
  12. 2025s3: You Don't Need That Much Data to Train a Search Agent via RL20 May
9 more
  1. 2025Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning20 May
  2. 2025Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent12 May
  3. 2025Patience is all you need! An agentic system for performing scientific literature review28 Mar
  4. 2025Open Deep Search: Democratizing Search with Open-source Reasoning Agents26 Mar
  5. 2025Retrieval Augmented Generation for Topic Modeling in Organizational Research: An Introduction with Empirical Demonstration28 Feb
  6. 2025PaSa: An LLM Agent for Comprehensive Academic Paper Search17 Jan
  7. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  8. 2024Level-Navi Agent: A Framework and benchmark for Chinese Web Search Agents20 Dec
  9. 2024Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents27 Feb

Other references · 117

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  3. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  8. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  9. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  10. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  11. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  12. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
38 more
  1. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  2. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  3. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  4. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  5. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  6. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 647
  7. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  8. 2020Fact or Fiction: Verifying Scientific Claimscited by 554
  9. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  10. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 335
  11. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  12. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challengescited by 282
  13. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?cited by 223
  14. 2020HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verificationcited by 201
  15. 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 167
  16. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 124
  17. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 122
  18. 2025xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluationscited by 120
  19. 2022End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Modelscited by 107
  20. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  21. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 94
  22. 2023ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendationcited by 77
  23. 2024RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generationcited by 75
  24. 2025SealQA: Raising the Bar for Reasoning in Search-Augmented Language Modelscited by 75
  25. 2023Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Taskscited by 73
  26. 2025MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflowcited by 73
  27. 2024Can Language Models Solve Olympiad Programming?cited by 72
  28. 2025VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learningcited by 68
  29. 2024MindSearch: Mimicking Human Minds Elicits Deep AI Searchercited by 66
  30. 2024Large Language Models Empowered Personalized Web Agentscited by 66
  31. 2025ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agentscited by 66
  32. 2024MACRec: a Multi-Agent Collaboration Framework for Recommendationcited by 58
  33. 2025Atom of Thoughts for Markov LLM Test-Time Scalingcited by 54
  34. 2020IIRC: A Dataset of Incomplete Information Reading Comprehension Questionscited by 53
  35. 2024Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learningcited by 51
  36. 2024Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answeringcited by 51
  37. 2021Fool Me Twice: Entailment from Wikipedia Gamificationcited by 50
  38. 2025DeepShop: A Benchmark for Deep Research Shopping Agentscited by 46

50 most cited of 117 All 117 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 17; 2026: 45.

62 papers.

Sort:

By area:

  1. 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 74
  2. 2025A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Modelscited by 38
  3. 2025Search Self-play: Pushing the Frontier of Agent Capability without Supervisioncited by 34
  4. 2025StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Modelscited by 26
  5. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 22
  6. 2025DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seekingcited by 21
  7. 2026OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMscited by 21
  8. 2025Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Windowcited by 19
  9. 2025AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applicationscited by 17
  10. 2026Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptionscited by 17
  11. 2026TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agentscited by 16
  12. 2025Reinforcement Learning Foundations for Deep Research Systems: A Surveycited by 14
38 more
  1. 2025APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Trainingcited by 11
  2. 2026Efficient LLM Serving for Agentic Workflows: A Data Systems Perspectivecited by 11
  3. 2026Towards Long-horizon Agentic Multimodal Searchcited by 11
  4. 2025VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seekingcited by 10
  5. 2025ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Modelscited by 10
  6. 2026Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agentscited by 10
  7. 2026Cross-Tokenizer LLM Distillation through a Byte-Level Interfacecited by 8
  8. 2025Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agentscited by 7
  9. 2025Stop DDoS Attacking the Research Community with AI-Generated Survey Paperscited by 7
  10. 2025AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Constructioncited by 7
  11. 2025Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMscited by 6
  12. 2026GISA: A Benchmark for General Information-Seeking Assistantcited by 6
  13. 2025SafeSearch: Automated Red-Teaming of LLM-Based Search Agentscited by 4
  14. 2025ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Callingcited by 4
  15. 2026Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generationcited by 4
  16. 2026AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Webcited by 4
  17. 2026CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposingcited by 4
  18. 2026Learning to Retrieve from Agent Trajectoriescited by 3
  19. 2026Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generationcited by 3
  20. 2026ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agentscited by 3
  21. 2026PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrievalcited by 2
  22. 2026T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoningcited by 2
  23. 2026Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agentscited by 2
  24. 2026R^2-Mem: Reflective Experience for Memory Searchcited by 2
  25. 2026Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agentscited by 2
  26. 2026CAFE: Self-Improving Search Agents Need Co-Evolving Feedbackcited by 2
  27. 2026One Policy, Any Budget: Internalizing Budget-Aware Search via Reinforcement Learningcited by 2
  28. 2026Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMscited by 1
  29. 2026Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Sciencecited by 1
  30. 2026Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibrationcited by 1
  31. 2026Rethinking Agentic Reinforcement Learning In Large Language Modelscited by 1
  32. 2026SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platformscited by 1
  33. 2026DeepRefine: Agentic Knowledge Refinement via Reinforcement Learningcited by 1
  34. 2026When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Searchcited by 1
  35. 2026WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Searchcited by 1
  36. 2026Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agentscited by 1
  37. 2026Fact-Checking with Large Language Models via Probabilistic Certainty and Consistencycited by 0
  38. 2026Story2Proposal: A Scaffold for Structured Scientific Paper Writingcited by 0

50 most cited of 62 All 62 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval
  2. 2025Towards AI Search Paradigm
  3. 2025Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents
  4. 2025Deep Research: A Survey of Autonomous Research Agents
  5. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects
  6. 2026OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
  7. 2026Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents
  8. 2023The Rise and Potential of Large Language Model Based Agents: A Survey