RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning
Authors:
- Yucan GuoYGYucan Guo
- Miao SuMSMiao Su
- Saiping GuanSGSaiping Guan
- Zihao SunZSZihao Sun
- Xiaolong JinXJXiaolong Jin
- Jiafeng GuoJGJiafeng Guo
- Xueqi ChengXCXueqi Cheng
Preprint
Abstract
Retrieval-Augmented Generation (RAG) integrates non-parametric knowledge into Large Language Models (LLMs), typically from unstructured texts and structured graphs. While recent progress has advanced text-based RAG to multi-turn reasoning through Reinforcement Learning (RL), extending these advances to hybrid retrieval introduces additional challenges. Existing graph-based or hybrid systems typically depend on fixed or handcrafted retrieval pipelines, lacking the ability to integrate supplementary evidence as reasoning unfolds. Besides, while graph evidence provides relational structures crucial for multi-hop reasoning, it is substantially more expensive to retrieve. To address these limitations, we introduce \model{}, an RL-based framework that enables LLMs to perform multi-turn and adaptive graph-text hybrid RAG. \model{} jointly optimizes the entire generation process via RL, allowing the model to learn when to reason, what to retrieve from either texts or graphs, and when to produce final answers, all within a unified generation policy. To guide this learning process, we design a two-stage training framework that accounts for both task outcome and retrieval efficiency, enabling the model to exploit hybrid evidence while avoiding unnecessary retrieval overhead. Experimental results across five question answering benchmarks demonstrate that \model{} significantly outperforms existing RAG baselines, highlighting the benefits of end-to-end RL in supporting adaptive and efficient retrieval for complex reasoning.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Graph Retrieval-Augmented Generation: A SurveyACM Transactions on Information Systems, 2025
- HybridFlow: A Flexible and Efficient RLHF Framework2025
- A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open QuestionsACM Transactions on Information Systems, 2025
- Search-o1: Agentic Search-Enhanced Large Reasoning Models2025
- Factuality challenges in the era of large language models and opportunities for fact-checkingNature Machine Intelligence, 2024
- Efficient Memory Management for Large Language Model Serving with PagedAttention2023
- ♫ MuSiQue: Multihop Questions via Single-hop Question CompositionTransactions of the Association for Computational Linguistics, 2022
- A Survey of Knowledge-enhanced Text GenerationACM Computing Surveys, 2022
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019
- Reciprocal rank fusion outperforms condorcet and individual rank learning methods2009