mlsanityData to 14 Oct 2026

From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents

arXiv 2506.18959 ↗First posted 23 Jun 2025cs.IR cs.CL cs.LGcited by 51

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex, multi-step information needs. Our position is that Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research. These systems transcend conventional information search techniques by tightly integrating autonomous reasoning, iterative retrieval, and information synthesis into a dynamic feedback loop. We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn. We also introduce a test-time scaling law to formalize the impact of computational depth on reasoning and search. Supported by benchmark results and the rise of open-source implementations, 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. All the related resources, including industry products, research papers, benchmark datasets, and open-source implementations, are collected for the community in https://github.com/DavidZWZ/Awesome-Deep-Research.

Key facts. Cited by 51 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 83 of its 108 references that are in the map. First posted on arXiv 23 Jun 2025.

Builds on

83 of 108 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent12 May
  2. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capability30 Apr
  3. 2025Open Deep Search: Democratizing Search with Open-source Reasoning Agents26 Mar
  4. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning25 Mar
  5. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  6. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning7 Mar
  7. 2025ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding14 Jan
  8. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  9. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec

Other references · 74

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2017Graph Attention Networkscited by 8,923
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  7. 2017Inductive Representation Learning on Large Graphscited by 6,320
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  9. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  10. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  11. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  12. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
38 more
  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  2. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  4. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  5. 2025s1: Simple test-time scalingcited by 1,341
  6. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  7. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  8. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  9. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  10. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  11. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 647
  12. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  13. 2023Active Retrieval Augmented Generationcited by 516
  14. 2025Humanity's Last Examcited by 491
  15. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 464
  16. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  17. 2024Understanding the planning of LLM agents: A surveycited by 421
  18. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  19. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 353
  20. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  21. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 286
  22. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  23. 2022OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalizationcited by 236
  24. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matterscited by 222
  25. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213
  26. 2024ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Modelscited by 210
  27. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 208
  28. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 205
  29. 2023Can LLM-Generated Misinformation Be Detected?cited by 177
  30. 2025WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learningcited by 165
  31. 2023Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Modelscited by 154
  32. 2025BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinesecited by 145
  33. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 119
  34. 2024From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflectioncited by 98
  35. 2022Evaluating the Factual Consistency of Large Language Models Through News Summarizationcited by 92
  36. 2024A Closer Look at the Limitations of Instruction Tuningcited by 77
  37. 2024Inference Scaling for Long-Context Retrieval Augmented Generationcited by 65
  38. 2024Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questionscited by 54

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 20; 2026: 31.

51 papers.

Sort:

By area:

  1. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 62
  2. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  3. 2025Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agentscited by 48
  4. 2026Dr. Zero: Self-Evolving Search Agents without Training Datacited by 44
  5. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 44
  6. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 42
  7. 2025UserRL: Training Interactive User-Centric Agent via Reinforcement Learningcited by 32
  8. 2025A Survey on Agentic Multimodal Large Language Modelscited by 23
  9. 2026MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baselinecited by 20
  10. 2026Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptionscited by 17
  11. 2026MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalizationcited by 17
  12. 2026TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agentscited by 16
38 more
  1. 2025ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agentscited by 15
  2. 2025DynaSearcher: Dynamic Knowledge Graph Augmented Search Agent via Multi-Reward Reinforcement Learningcited by 14
  3. 2025FinDeepResearch: Evaluating Deep Research Agents in Rigorous Financial Analysiscited by 14
  4. 2026RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewardscited by 12
  5. 2025GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalizationcited by 11
  6. 2025An Information Theoretic Perspective on Agentic System Designcited by 8
  7. 2025InfoAgent: Advancing Autonomous Information-Seeking Agentscited by 7
  8. 2025Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safetycited by 7
  9. 2026Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generationcited by 7
  10. 2025SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMscited by 6
  11. 2025Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologiescited by 5
  12. 2026Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planningcited by 5
  13. 2026From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Searchcited by 5
  14. 2026RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skillscited by 4
  15. 2025Dr. Bench: A Multidimensional Evaluation for Deep Research Agents, from Answers to Reportscited by 3
  16. 2026Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert Taxonomiescited by 3
  17. 2026Scaling Small Agents Through Strategy Auctionscited by 3
  18. 2026EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agentscited by 3
  19. 2025Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Frameworkcited by 2
  20. 2025MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extractioncited by 2
  21. 2025ADRA-Bank: A Modular Benchmark for Academic Deep Research Agentscited by 2
  22. 2026IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learningcited by 2
  23. 2025Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generationcited by 1
  24. 2025CompAgent: An Agentic Framework for Visual Compliance Verificationcited by 1
  25. 2026HotelQuEST: Balancing Quality and Efficiency in Agentic Searchcited by 1
  26. 2026Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reportscited by 1
  27. 2026FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Searchcited by 1
  28. 2026A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensionscited by 1
  29. 2026MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoningcited by 1
  30. 2026FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflowscited by 1
  31. 2026False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agentscited by 1
  32. 2026Fact-Checking with Large Language Models via Probabilistic Certainty and Consistencycited by 0
  33. 2026Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Searchcited by 0
  34. 2026The First Drop of Ink: Nonlinear Impact of Distracting Information in Long-Context Reasoningcited by 0
  35. 2026Multi-Head Recurrent Memory Agentscited by 0
  36. 2026SciDataSailor: Deep Scientific Data Exploringcited by 0
  37. 2026Contextual Information Policy Optimization for Search Agentscited by 0
  38. 2026Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agentscited by 0

50 most cited of 51 All 51 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
  2. 2026Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks
  3. 2025Deep Research: A Survey of Autonomous Research Agents
  4. 2025DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking
  5. 2026EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
  6. 2026Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
  7. 2025RAVine: Reality-Aligned Evaluation for Agentic Search
  8. 2026AgentIR: Reasoning-Aware Retrieval for Deep Research Agents