mlsanityData to 7 Oct 2026

ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation

arXiv 2503.21729 ↗First posted 27 Mar 2025cs.CL cs.AIcited by 13

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

also in 1 more
Abstract (arXiv)

Large Reasoning Models (LRMs) exhibit remarkable reasoning abilities but rely primarily on parametric knowledge, limiting factual accuracy. While recent works equip reinforcement learning (RL)-based LRMs with retrieval capabilities, they suffer from overthinking and lack robustness in reasoning, reducing their effectiveness in question answering (QA) tasks. To address this, we propose ReaRAG, a factuality-enhanced reasoning model that explores diverse queries without excessive iterations. Our solution includes a novel data construction framework with an upper bound on the reasoning chain length. Specifically, we first leverage an LRM to generate deliberate thinking, then select an action from a predefined action space (Search and Finish). For Search action, a query is executed against the RAG engine, where the result is returned as observation to guide reasoning steps later. This process iterates until a Finish action is chosen. Benefiting from ReaRAG's strong reasoning capabilities, our approach outperforms existing baselines on multi-hop QA. Further analysis highlights its strong reflective ability to recognize errors and refine its reasoning trajectory. Our study enhances LRMs' factuality while effectively integrating robust reasoning for Retrieval-Augmented Generation (RAG).

Key facts. Cited by 13 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 18 of its 42 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

18 of 42 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning25 Mar
  2. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning7 Mar
  3. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  4. 2024RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement17 Dec
  5. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation19 Sep

Other references · 13

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  2. 2024Qwen2.5 Technical Reportcited by 4,713
  3. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  4. 2025s1: Simple test-time scalingcited by 1,311
  5. 2024OpenAI o1 System Cardcited by 1,220
  6. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193
  7. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,096
  8. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 564
  9. 2023Textbooks Are All You Needcited by 561
  10. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 405
  11. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 291
  12. 2024Corrective Retrieval Augmented Generationcited by 187
1 more
  1. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 144

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 2.

13 papers.

Sort:

By area:

  1. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  2. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 40
  3. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  4. 2025Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premisescited by 9
  5. 2025EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notescited by 8
  6. 2025WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflectioncited by 6
  7. 2025Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimizationcited by 5
  8. 2025MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Modelscited by 4
  9. 2025Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledgecited by 3
  10. 2025Improving Factuality in LLMs via Inference-Time Knowledge Graph Constructioncited by 2
  11. 2026MG2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generationcited by 1
  12. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAGcited by 0
1 more
  1. 2026The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
  2. 2025From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs
  3. 2025OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval
  4. 2025UR2: Unify RAG and Reasoning through Reinforcement Learning
  5. 2026PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering
  6. 2025RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism
  7. 2025Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
  8. 2025Reinforcement Fine-Tuning for Reasoning towards Multi-Step Multi-Source Search in Large Language Models