mlsanityData to 7 Oct 2026

WebThinker: Empowering Large Reasoning Models with Deep Research Capability

arXiv 2504.21776 ↗First posted 30 Apr 2025cs.CL cs.AI cs.IRcited by 320

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

Abstract (arXiv)

Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate impressive long-horizon reasoning capabilities. However, their reliance on static internal knowledge limits their performance on complex, knowledge-intensive tasks and hinders their ability to produce comprehensive research reports requiring synthesis of diverse web information. To address this, we propose WebThinker, a deep research agent that empowers LRMs to autonomously search the web, navigate among web pages, and draft reports during the reasoning process. WebThinker integrates a Deep Web Explorer module, enabling LRMs to dynamically search, navigate, and extract information from the web when encountering knowledge gaps. It also employs an Autonomous Think-Search-and-Draft strategy, allowing the model to seamlessly interleave reasoning, information gathering, and report writing in real time. To further enhance research tool utilization, we introduce an RL-based training strategy via iterative online Direct Preference Optimization (DPO). Extensive experiments on complex reasoning benchmarks (GPQA, GAIA, WebWalkerQA, HLE) and scientific report generation tasks (Glaive) demonstrate that WebThinker significantly outperforms existing methods and strong proprietary systems. Our approach enhances LRM reliability and applicability in complex scenarios, paving the way for more capable and versatile deep research systems. The code is available at https://github.com/RUC-NLPIR/WebThinker.

Key facts. Cited by 320 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 59 of its 76 references that are in the map. First posted on arXiv 30 Apr 2025.

Builds on

59 of 76 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025RARE: Retrieval-Augmented Reasoning Modeling30 Mar
  2. 2025MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search26 Mar
  3. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning25 Mar
  4. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  5. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning7 Mar
  6. 2025Chain-of-Retrieval Augmented Generation24 Jan
  7. 2025OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking16 Jan
  8. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  9. 2024RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement17 Dec
  10. 2024How Much Can RAG Help the Reasoning of LLM?3 Oct

Other references · 49

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  7. 2024Qwen2.5 Technical Reportcited by 4,713
  8. 2024GPT-4o System Cardcited by 4,467
  9. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  10. 2024Qwen2 Technical Reportcited by 2,076
  11. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  12. 2024Qwen2.5-Coder Technical Reportcited by 1,151
37 more
  1. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  2. 2020Scaling Laws for Autoregressive Generative Modelingcited by 510
  3. 2025Humanity's Last Examcited by 467
  4. 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Modelcited by 450
  5. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  6. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 377
  7. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 357
  8. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  9. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  10. 2025ToolRL: Reward is All Tool Learning Needscited by 342
  11. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  12. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 268
  13. 2025Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learningcited by 260
  14. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  15. 2024Self-Play Preference Optimization for Language Model Alignmentcited by 228
  16. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 211
  17. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 171
  18. 2025ToRL: Scaling Tool-Integrated RLcited by 166
  19. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systemscited by 162
  20. 2023Query2doc: Query Expansion with Large Language Modelscited by 146
  21. 2024O1 Replication Journey: A Strategic Progress Report -- Part 1cited by 140
  22. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  23. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  24. 2025NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questionscited by 81
  25. 2025An Empirical Study on Eliciting and Improving R1-like Reasoning Modelscited by 78
  26. 2024Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Modelscited by 73
  27. 2024Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problemscited by 49
  28. 2024Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMscited by 34
  29. 2025Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineeringcited by 34
  30. 2024BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidencecited by 28
  31. 2024Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generationcited by 27
  32. 2024Metacognitive Retrieval-Augmented Large Language Modelscited by 26
  33. 2024RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generationcited by 20
  34. 2025Reasoning Beyond Limits: Advances and Open Problems for LLMscited by 16
  35. 2024Toward General Instruction-Following Alignment for Retrieval-Augmented Generationcited by 9
  36. 2025DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinkingcited by 9
  37. 2024AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistantcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 145; 2026: 175.

320 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2025DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agentscited by 236
  3. 2025WebSailor: Navigating Super-human Reasoning for Web Agentcited by 218
  4. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 203
  5. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  6. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  7. 2025Agentic Reinforced Policy Optimizationcited by 166
  8. 2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLcited by 144
  9. 2025Scaling Long-Horizon LLM Agent via Context-Foldingcited by 136
  10. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 122
  11. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  12. 2025WebShaper: Agentically Data Synthesizing via Information-Seeking Formalizationcited by 118
38 more
  1. 2025WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agentcited by 114
  2. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Managementcited by 95
  3. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 90
  4. 2025WebExplorer: Explore and Evolve for Training Long-Horizon Web Agentscited by 86
  5. 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RLcited by 75
  6. 2025Tree Search for LLM Agent Reinforcement Learningcited by 73
  7. 2025MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scalingcited by 72
  8. 2025Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learningcited by 67
  9. 2025WideSearch: Benchmarking Agentic Broad Info-Seekingcited by 66
  10. 2025WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agentscited by 66
  11. 2025Deep Research: A Survey of Autonomous Research Agentscited by 63
  12. 2025Scaling Test-time Compute for LLM Agentscited by 59
  13. 2025WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learningcited by 59
  14. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  15. 2025SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesiscited by 55
  16. 2025Visual Agentic Reinforcement Fine-Tuningcited by 53
  17. 2025DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RLcited by 53
  18. 2025Tongyi DeepResearch Technical Reportcited by 53
  19. 2025MiniCPM4: Ultra-Efficient LLMs on End Devicescited by 51
  20. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agentscited by 49
  21. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  22. 2026EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesiscited by 46
  23. 2025SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?cited by 45
  24. 2025SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agentcited by 44
  25. 2025Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Trainingcited by 42
  26. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 40
  27. 2025Scaling Agents via Continual Pre-trainingcited by 39
  28. 2026Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligencecited by 35
  29. 2025ReportBench: Evaluating Deep Research Agents via Academic Survey Taskscited by 34
  30. 2025Mitigating Overthinking in Large Reasoning Models via Manifold Steeringcited by 32
  31. 2025Demystifying Reinforcement Learning in Agentic Reasoningcited by 32
  32. 2025MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool usecited by 30
  33. 2025Characterizing Deep Research: A Benchmark and Formal Definitioncited by 29
  34. 2025SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agentscited by 29
  35. 2026MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verificationcited by 28
  36. 2025Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Executioncited by 27
  37. 2025TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Roboticscited by 27
  38. 2025Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Rewardcited by 25

50 most cited of 320 All 320 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
  2. 2025A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications
  3. 2025Deep Research Bench: Evaluating AI Web Research Agents
  4. 2025Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction
  5. 2026Hypothesis-Driven Deep Research with Large Language Models: A Structured Methodology for Automated Knowledge Discovery
  6. 2026EcoThink: A Green Adaptive Inference Framework for Sustainable and Accessible Agents
  7. 2025Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
  8. 2025Open Data Synthesis For Deep Research