mlsanityData to 14 Oct 2026

KunLunBaizeRAG: Reinforcement Learning Driven Inference Performance Leap for Large Language Models

arXiv 2506.19466 ↗First posted 24 Jun 2025cs.AIcited by 0

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

Abstract (arXiv)

This paper introduces KunLunBaizeRAG, a reinforcement learning-driven reasoning framework designed to enhance the reasoning capabilities of large language models (LLMs) in complex multi-hop question-answering tasks. The framework addresses key limitations of traditional RAG, such as retrieval drift, information redundancy, and strategy rigidity. Key innovations include the RAG-driven Reasoning Alignment (RDRA) mechanism, the Search-Think Iterative Enhancement (STIE) mechanism, the Network-Local Intelligent Routing (NLR) mechanism, and a progressive hybrid training strategy. Experimental results demonstrate significant improvements in exact match (EM) and LLM-judged score (LJ) across four benchmarks, highlighting the framework's robustness and effectiveness in complex reasoning scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 27 of its 30 references that are in the map. First posted on arXiv 24 Jun 2025.

Builds on

27 of 30 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  2. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec

Other references · 25

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  8. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  9. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  10. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  11. 2025s1: Simple test-time scalingcited by 1,341
  12. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
13 more
  1. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  2. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  3. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  4. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  5. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  6. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  7. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agentscited by 339
  8. 2024Corrective Retrieval Augmented Generationcited by 197
  9. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 166
  10. 2022Dense Text Retrieval based on Pretrained Language Models: A Surveycited by 136
  11. 2024Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuningcited by 42
  12. 2024Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphscited by 24
  13. 2024Baichuan Alignment Technical Reportcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Multi-hop Reasoning via Early Knowledge Alignment
  2. 2025RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism
  3. 2025UR2: Unify RAG and Reasoning through Reinforcement Learning
  4. 2026AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering
  5. 2026PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering
  6. 2025Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning
  7. 2025REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question Answering
  8. 2026KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement Learning