mlsanityData to 14 Oct 2026

DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning

arXiv 2503.00223 ↗First posted 28 Feb 2025cs.IRcited by 66

Not on the map. Why?

Cited by 25 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely on expensive supervised learning or distillation techniques that require significant computational resources and hand-labeled data. We introduce DeepRetrieval, a reinforcement learning (RL) approach that trains LLMs for query generation through trial and error without supervised data (reference query). Using retrieval metrics as rewards, our system generates queries that maximize retrieval performance. DeepRetrieval outperforms leading methods on literature search with 65.07% (vs. previous SOTA 24.68%) recall for publication search and 63.18% (vs. previous SOTA 32.11%) recall for trial search using real-world search engines. DeepRetrieval also dominates in evidence-seeking retrieval, classic information retrieval and SQL database search. With only 3B parameters, it outperforms industry-leading models like GPT-4o and Claude-3.5-Sonnet on 11/13 datasets. These results demonstrate that our RL approach offers a more efficient and effective paradigm for information retrieval. Our data and code are available at: https://github.com/pat-jj/DeepRetrieval.

Key facts. Cited by 66 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Feb 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

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

66 papers.

Sort:

By area:

  1. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  2. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  3. 2025VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Usecited by 96
  4. 2025StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimizationcited by 88
  5. 2025VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learningcited by 68
  6. 2025Deep Research: A Survey of Autonomous Research Agentscited by 66
  7. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  8. 2025Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agentscited by 48
  9. 2025Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoningcited by 35
  10. 2025A Survey of Personalization: From RAG to Agentcited by 27
  11. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  12. 2025SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMscited by 24
38 more
  1. 2026RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL Systemcited by 24
  2. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challengescited by 19
  3. 2025Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Usecited by 16
  4. 2025Generative AI Act II: Test Time Scaling Drives Cognition Engineeringcited by 15
  5. 2025Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learningcited by 14
  6. 2025RollArt: Disaggregated Multi-Task Agentic RL Training at Scalecited by 14
  7. 2026SmartSearch: Process Reward-Guided Query Refinement for Search Agentscited by 14
  8. 2025Position: The Real Barrier to LLM Agent Usability is Agentic ROIcited by 12
  9. 2026RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewardscited by 12
  10. 2025TongSearch-QR: Reinforced Query Reasoning for Retrievalcited by 11
  11. 2025Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learningcited by 10
  12. 2026Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnessescited by 10
  13. 2025ReZero: Enhancing LLM search ability by trying one-more-timecited by 9
  14. 2025Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigmcited by 9
  15. 2026Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoningcited by 9
  16. 2025Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learningcited by 8
  17. 2025MuaLLM: A Multimodal Large Language Model Agent for Circuit Design Assistance with Hybrid Contextual Retrieval-Augmented Generationcited by 8
  18. 2025A Survey on Retrieval And Structuring Augmented Generation with Large Language Modelscited by 8
  19. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  20. 2025AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Constructioncited by 7
  21. 2026MoCo: A One-Stop Shop for Model Collaboration Researchcited by 6
  22. 2026EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generationcited by 6
  23. 2025Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Modelscited by 5
  24. 2025PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoningcited by 4
  25. 2026MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoningcited by 4
  26. 2025Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learningcited by 3
  27. 2025Rethinking On-policy Optimization for Query Augmentationcited by 3
  28. 2025Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generationcited by 2
  29. 2026RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agentscited by 2
  30. 2026DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoningcited by 2
  31. 2026Scaling Participation in Modular AI Systemscited by 2
  32. 2026RL-Index: Reinforcement Learning for Retrieval Index Reasoningcited by 2
  33. 2026From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Spacecited by 2
  34. 2026Antares: Foundation Models for Agentic Vulnerability Localizationcited by 2
  35. 2026It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learningcited by 2
  36. 2025SAGE: Strategy-Adaptive Generation Engine for Query Rewritingcited by 1
  37. 2025Sherlock Your Queries: Learning to Ask the Right Questions for Dialogue-Based Retrievalcited by 1
  38. 2026MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learningcited by 1

50 most cited of 66 All 66 (JSON)