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

2025/06/24 by Li, Cheng, Liu, Jiexiong, Chen, Yixuan +2
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2506.19466

Abstract

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.

Citations

• s1: Simple test-time scaling
• DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning
• Qwen2.5 Technical Report
• Baichuan Alignment Technical Report
• Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs
• BioXP-0.5B: Explainable Medical-AI via RL-GRPO
• Corrective Retrieval Augmented Generation
• AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
• Retrieval-Augmented Generation for Large Language Models: A Survey
• CareerX: A Retrieval-Augmented Generation Framework for Personalized AI-Driven Career Guidance
• Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions
• Text Embeddings by Weakly-Supervised Contrastive Pre-training
• Dense Text Retrieval based on Pretrained Language Models: A Survey
• Dense Text Retrieval Based on Pretrained Language Models: A Survey
• Measuring and Narrowing the Compositionality Gap in Language Models
• STaR: Bootstrapping Reasoning With Reasoning
• BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
• MuSiQue: Multihop Questions via Single-hop Question Composition
• Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
• Dense Passage Retrieval for Open-Domain Question Answering
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Related

• Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
• RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism
• Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models
• Interleaved Reasoning for Large Language Models via Reinforcement Learning
• A Survey of Reinforcement Learning for Large Reasoning Models