mlsanityData to 14 Oct 2026

SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis

arXiv 2505.16834 ↗First posted 22 May 2025cs.CL cs.AI cs.IRcited by 55

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

also in 1 more
Abstract (arXiv)

Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios requiring multi-step reasoning and iterative information retrieval. However, existing approaches face critical limitations that lack high-quality training trajectories or suffer from the distributional mismatches in simulated environments and prohibitive computational costs for real-world deployment. This paper introduces SimpleDeepSearcher, a lightweight yet effective framework that bridges this gap through strategic data engineering rather than complex training paradigms. Our approach synthesizes high-quality training data by simulating realistic user interactions in live web search environments, coupled with a multi-criteria curation strategy that optimizes the diversity and quality of input and output side. Experiments on five benchmarks across diverse domains demonstrate that SFT on only 871 curated samples yields significant improvements over RL-based baselines. Our work establishes SFT as a viable pathway by systematically addressing the data-scarce bottleneck, offering practical insights for efficient deep search systems. Our code is available at https://github.com/RUCAIBox/SimpleDeepSearcher.

Key facts. Cited by 55 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 27 of its 40 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

27 of 40 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capability30 Apr
  2. 2025Open Deep Search: Democratizing Search with Open-source Reasoning Agents26 Mar
  3. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  4. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning7 Mar
  5. 2025Chain-of-Retrieval Augmented Generation24 Jan
  6. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  7. 2024RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement17 Dec
  8. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation19 Sep
  9. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec

Other references · 18

  1. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  2. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  3. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  4. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  5. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 647
  6. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  7. 2024Measuring short-form factuality in large language modelscited by 373
  8. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  9. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  10. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 286
  11. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 257
  12. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 208
6 more
  1. 2025BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinesecited by 145
  2. 2020How Can We Accelerate Progress Towards Human-like Linguistic Generalization?cited by 114
  3. 2024MindSearch: Mimicking Human Minds Elicits Deep AI Searchercited by 66
  4. 2025Atom of Thoughts for Markov LLM Test-Time Scalingcited by 54
  5. 2022Don't Blame the Annotator: Bias Already Starts in the Annotation Instructionscited by 47
  6. 2020Answering Open-Domain Questions of Varying Reasoning Steps from Textcited by 43

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 33; 2026: 22.

55 papers.

Sort:

By area:

  1. 2025UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learningcited by 215
  2. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  3. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
  4. 2025Agentic Reinforced Policy Optimizationcited by 172
  5. 2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLcited by 150
  6. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 128
  7. 2025WebShaper: Agentically Data Synthesizing via Information-Seeking Formalizationcited by 121
  8. 2025VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Usecited by 96
  9. 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RLcited by 80
  10. 2025Deep Research: A Survey of Autonomous Research Agentscited by 66
  11. 2025DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RLcited by 55
  12. 2025Search Self-play: Pushing the Frontier of Agent Capability without Supervisioncited by 34
38 more
  1. 2026Gen-Searcher: Reinforcing Agentic Search for Image Generationcited by 30
  2. 2025Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Executioncited by 27
  3. 2025MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learningcited by 27
  4. 2025Towards Effective Code-Integrated Reasoningcited by 23
  5. 2026Terminal-World: Scaling Terminal-Agent Environments via Agent Skillscited by 20
  6. 2025BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actionscited by 17
  7. 2025Open Data Synthesis For Deep Researchcited by 16
  8. 2026ClawGym: A Scalable Framework for Building Effective Claw Agentscited by 15
  9. 2025ParallelMuse: Agentic Parallel Thinking for Deep Information Seekingcited by 14
  10. 2025Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Searchcited by 12
  11. 2025Repurposing Synthetic Data for Fine-grained Search Agent Supervisioncited by 11
  12. 2026Agentic-R: Learning to Retrieve for Agentic Searchcited by 11
  13. 2026Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaborationcited by 11
  14. 2026Towards Long-horizon Agentic Multimodal Searchcited by 11
  15. 2026GrepSeek: Training Search Agents for Direct Corpus Interactioncited by 10
  16. 2025Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AIcited by 8
  17. 2025LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Servicescited by 8
  18. 2026GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidencecited by 7
  19. 2026FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agentscited by 7
  20. 2025Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrievalcited by 6
  21. 2025MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoningcited by 6
  22. 2025From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMscited by 5
  23. 2025Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMscited by 5
  24. 2025Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Modelscited by 5
  25. 2026Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalizationcited by 5
  26. 2025FrugalRAG: Less is More in RL Finetuning for Multi-Hop Question Answeringcited by 4
  27. 2025Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agentscited by 4
  28. 2026DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agentscited by 4
  29. 2025What Limits Agentic Systems Efficiency?cited by 3
  30. 2026InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioningcited by 3
  31. 2026Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Promptscited by 3
  32. 2026CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Searchcited by 3
  33. 2026Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Trainingcited by 3
  34. 2026Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?cited by 3
  35. 2025A Vision for Geo-Temporal Deep Research Systems: Towards Comprehensive, Transparent, and Reproducible Geo-Temporal Information Synthesiscited by 2
  36. 2026SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Planscited by 2
  37. 2026ORBIT: Scalable and Verifiable Data Generation for Search Agents on a Tight Budgetcited by 2
  38. 2026Self-Evolving Deep Research via Joint Generation and Evaluationcited by 2

50 most cited of 55 All 55 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework
  2. 2025InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation
  3. 2025Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics
  4. 2025LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers
  5. 2025Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning
  6. 2025DeepDiver: Adaptive Search Intensity Scaling via Open-Web Reinforcement Learning
  7. 2026REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
  8. 2025Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning