mlsanityData to 14 Oct 2026

RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism

arXiv 2507.02962 ↗First posted 30 Jun 2025cs.CL cs.AI cs.IRcited by 16

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

Abstract (arXiv)

Large Language Models (LLMs), despite their remarkable capabilities, are prone to generating hallucinated or outdated content due to their static internal knowledge. While Retrieval-Augmented Generation (RAG) integrated with Reinforcement Learning (RL) offers a solution, these methods are fundamentally constrained by a single-query mode, leading to prohibitive latency and inherent brittleness. To overcome these limitations, we introduce RAG-R1, a novel two-stage training framework centered around multi-query parallelism. Our framework enables LLMs to adaptively leverage internal and external knowledge during the reasoning process while transitioning from the single-query mode to multi-query parallelism. This architectural shift bolsters reasoning robustness while significantly reducing inference latency. Extensive experiments on seven question-answering benchmarks confirm the superiority of our method, which outperforms the strongest baseline by up to 13.7% and decreases inference time by 11.1%.

Key facts. Cited by 16 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 28 of its 29 references that are in the map. First posted on arXiv 30 Jun 2025.

Builds on

28 of 29 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  2. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  3. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec

Other references · 25

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  6. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  8. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  9. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  10. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  11. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  12. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
13 more
  1. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  2. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  3. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  4. 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 672
  5. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  6. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  7. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  8. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 262
  9. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 208
  10. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  11. 2025MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capabilitycited by 22
  12. 2024RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generationcited by 20
  13. 2024Multi-Aspect Reviewed-Item Retrieval via LLM Query Decomposition and Aspect Fusioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 10.

16 papers.

Sort:

By area:

  1. 2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLcited by 150
  2. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 62
  3. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 22
  4. 2025Reinforcement Learning Foundations for Deep Research Systems: A Surveycited by 14
  5. 2025Beneficial Reasoning Behaviors in Agentic Search and Effective Post-training to Obtain Themcited by 7
  6. 2026Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Rewardcited by 6
  7. 2026When Is Enough Not Enough? Illusory Completion in Search Agentscited by 5
  8. 2025Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoningcited by 4
  9. 2026SearchMaster: Grounded and Regulated Self-Play for Search Agentscited by 3
  10. 2026Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RLcited by 2
  11. 2026DOTRAG: Retrieval-Time Reasoning Along Pathscited by 1
  12. 2026Learning Adaptive Parallel Execution for Efficient Code Localizationcited by 0
4 more
  1. 2026StepGap: A Hybrid NLI-LLM Checker for Step-Level Evidence-Gap Detectionin Multi-Hop Question Answeringcited by 0
  2. 2026Foundation Agents Meet Agentic Deep Research: Evidence-Grounded Clinical Code Forecastingcited by 0
  3. 2026MCite-RL: Towards Reliable Multimodal RAG via Citation-enhanced Agentic Reinforcement Learningcited by 0
  4. 2026CASI: Credit Assignment via Set Intervention for Agentic Retrievalcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025UR2: Unify RAG and Reasoning through Reinforcement Learning
  2. 2025ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning
  3. 2025R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
  4. 2025MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval
  5. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
  6. 2025R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning
  7. 2025From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs
  8. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning