mlsanityData to 7 Oct 2026

Search-o1: Agentic Search-Enhanced Large Reasoning Models

arXiv 2501.05366 ↗First posted 9 Jan 2025cs.AI cs.CL cs.IRcited by 423

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

also in 1 more
Abstract (arXiv)

Large reasoning models (LRMs) like OpenAI-o1 have demonstrated impressive long stepwise reasoning capabilities through large-scale reinforcement learning. However, their extended reasoning processes often suffer from knowledge insufficiency, leading to frequent uncertainties and potential errors. To address this limitation, we introduce Search-o1, a framework that enhances LRMs with an agentic retrieval-augmented generation (RAG) mechanism and a Reason-in-Documents module for refining retrieved documents. Search-o1 integrates an agentic search workflow into the reasoning process, enabling dynamic retrieval of external knowledge when LRMs encounter uncertain knowledge points. Additionally, due to the verbose nature of retrieved documents, we design a separate Reason-in-Documents module to deeply analyze the retrieved information before injecting it into the reasoning chain, minimizing noise and preserving coherent reasoning flow. Extensive experiments on complex reasoning tasks in science, mathematics, and coding, as well as six open-domain QA benchmarks, demonstrate the strong performance of Search-o1. This approach enhances the trustworthiness and applicability of LRMs in complex reasoning tasks, paving the way for more reliable and versatile intelligent systems. The code is available at urlhttps://github.com/sunnynexus/Search-o1.

Key facts. Cited by 423 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 33 of its 53 references that are in the map. First posted on arXiv 9 Jan 2025.

Builds on

33 of 53 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024How Much Can RAG Help the Reasoning of LLM?3 Oct

Other references · 32

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  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. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2023Let's Verify Step by Stepcited by 3,598
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  9. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  10. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  11. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  12. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
20 more
  1. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  2. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  3. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 564
  4. 2020Scaling Laws for Autoregressive Generative Modelingcited by 510
  5. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  6. 2024ProcessBench: Identifying Process Errors in Mathematical Reasoningcited by 277
  7. 2024HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMscited by 257
  8. 2023The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learningcited by 251
  9. 2023How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Compositioncited by 222
  10. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systemscited by 162
  11. 2024O1 Replication Journey: A Strategic Progress Report -- Part 1cited by 140
  12. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 122
  13. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  14. 2024o1-Coder: an o1 Replication for Codingcited by 77
  15. 2024Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspectivecited by 49
  16. 2024Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMscited by 34
  17. 2024Progressive Multimodal Reasoning via Active Retrievalcited by 24
  18. 2024RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generationcited by 20
  19. 2024CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Taskscited by 18
  20. 2021Addressing Deep Learning Model Uncertainty in Long-Range Climate Forecasting with Late Fusioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 249; 2026: 174.

423 papers.

Sort:

By area:

  1. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  2. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  3. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  4. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  5. 2025Memory in the Age of AI Agentscited by 285
  6. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 268
  7. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 252
  8. 2025WebSailor: Navigating Super-human Reasoning for Web Agentcited by 218
  9. 2025UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learningcited by 205
  10. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 203
  11. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  12. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 180
38 more
  1. 2025Agentic Reinforced Policy Optimizationcited by 166
  2. 2025The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Taskscited by 150
  3. 2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLcited by 144
  4. 2025ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarizationcited by 132
  5. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyondcited by 131
  6. 2025EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecyclecited by 129
  7. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  8. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 122
  9. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 119
  10. 2025WebShaper: Agentically Data Synthesizing via Information-Seeking Formalizationcited by 118
  11. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Toolscited by 106
  12. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 90
  13. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  14. 2025StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimizationcited by 82
  15. 2026SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalizationcited by 82
  16. 2025ReasonIR: Training Retrievers for Reasoning Taskscited by 76
  17. 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RLcited by 75
  18. 2025Tree Search for LLM Agent Reinforcement Learningcited by 73
  19. 2025Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learningcited by 68
  20. 2025SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attributioncited by 68
  21. 2025VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learningcited by 68
  22. 2025In-the-Flow Agentic System Optimization for Effective Planning and Tool Usecited by 67
  23. 2025WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agentscited by 66
  24. 2025Deep Research: A Survey of Autonomous Research Agentscited by 63
  25. 2025Scaling Test-time Compute for LLM Agentscited by 59
  26. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  27. 2025SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesiscited by 55
  28. 2025Visual Agentic Reinforcement Fine-Tuningcited by 53
  29. 2025DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RLcited by 53
  30. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agentscited by 49
  31. 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Sciencecited by 49
  32. 2025Chain-of-Retrieval Augmented Generationcited by 48
  33. 2025START: Self-taught Reasoner with Toolscited by 47
  34. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  35. 2025Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinkingcited by 46
  36. 2025SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?cited by 45
  37. 2025Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agentscited by 43
  38. 2025Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agentscited by 43

50 most cited of 423 All 423 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026GRASP: GRanularity-Aware Search Policy for Agentic RAG
  2. 2025Knowledge-Aware Iterative Retrieval for Multi-Agent Systems
  3. 2026Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems
  4. 2025MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning
  5. 2026Agentic-R: Learning to Retrieve for Agentic Search
  6. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
  7. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
  8. 2026Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki