GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning

• URL: http://arxiv.org/abs/2604.16401v1
• Date: Tue, 31 Mar 2026 09:53:20 GMT
• Title: GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning
• Abstract summary: Graph-based retrieval-augmented generation (GraphRAG) has emerged as a powerful paradigm for knowledge-intensive question answering.<n>Existing GraphRAG systems are typically built in a one-size-fits-all manner, relying on a fixed retrieval framework and a single, often large and costly, generator LLM for all queries.<n>We propose GraphRAG-the, a cost-efficient framework that adopts a hierarchical routing strategy to coordinate heterogeneous GraphRAGs and generator LLMs.
• Score: 14.136365231796994
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph-based retrieval-augmented generation (GraphRAG) has recently emerged as a powerful paradigm for knowledge-intensive question answering, especially for tasks that require structured evidence organization and multi-hop reasoning. However, existing GraphRAG systems are typically built in a one-size-fits-all manner, relying on a fixed retrieval framework and a single, often large and costly, generator LLM for all queries. This static design limits their ability to adapt to the complexity of varying questions and often incurs unnecessary computational cost. To fill in the gap, we propose GraphRAG-Router, a cost-efficient framework that adopts a hierarchical routing strategy to coordinate heterogeneous GraphRAGs and generator LLMs. Specifically, GraphRAG-Router is first warmed up through supervised fine-tuning and then optimized with a two-stage reinforcement learning procedure, whose second stage introduces a curriculum cost-aware reward to encourage difficulty-aware and economical generator allocation. Extensive experiments on six general-domain and multi-hop QA benchmarks show that GraphRAG-Router consistently outperforms state-of-the-art baselines, reducing the overuse of large LLMs by nearly 30% while maintaining strong generalization capability.

Related papers

• Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems [9.226583502132753]
  Retrieval-augmented generation (RAG) and its graph-based extensions (GraphRAG) are effective paradigms for improving large language model (LLM) reasoning.<n>Recent agentic search systems enable dynamic, multi-round retrieval and sequential decision-making during inference.<n>We introduce RAGSearch, a unified benchmark that evaluates dense RAG and representative GraphRAG methods as retrieval infrastructures under agentic search.
  arXiv  Detail & Related papers  (2026-04-01T07:21:32Z)
• HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG [53.30561659838455]
  Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations.<n>Retrieval-Augmented Generation (RAG) frequently overlooks structural interdependencies essential for multi-hop reasoning.<n>Help achieves competitive performance across multiple simple and multi-hop QA benchmarks and up to a 28.8$times$ speedup over leading Graph-based RAG baselines.
  arXiv  Detail & Related papers  (2026-02-24T14:05:29Z)
• AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction [60.51319139563509]
  We introduce AutoGraph-R1, the first framework to directly optimize KG construction for task performance using Reinforcement Learning (RL)<n>We design two novel, task-aware reward functions, one for graphs as knowledge carriers and another as knowledge indices.<n>Our work shows it is possible to close the loop between construction and application, shifting the paradigm from building intrinsically good'' graphs to building demonstrably useful'' ones.
  arXiv  Detail & Related papers  (2025-10-17T06:03:36Z)
• LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora [17.929144506419064]
  Retrieval-Augmented Generation (RAG) is widely used to mitigate hallucinations of Large Language Models (LLMs) by leveraging external knowledge.<n>Existing graph-based RAG methods rely on unstable and costly relation extraction for graph construction.<n>We propose LinearRAG, an efficient framework that enables reliable graph construction and precise passage retrieval.
  arXiv  Detail & Related papers  (2025-10-11T08:43:45Z)
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models [59.72897499248909]
  We propose a novel graph retriever trained end-to-end with Large Language Models (LLMs)<n>Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together.<n>Our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-20T02:38:00Z)
• GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning [33.57411612551111]
  We propose GraphRAG-R1, an adaptive GraphRAG framework by training LLMs with process-constrained outcome-based reinforcement learning (RL)<n>Our method can decompose complex problems, autonomously invoke retrieval tools, and perform effective reasoning.<n>Our framework can be flexibly integrated with various existing retrieval methods, consistently delivering performance improvements.
  arXiv  Detail & Related papers  (2025-07-31T14:11:16Z)
• Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning [20.05893083101089]
  Graph-R1 is an agentic GraphRAG framework via end-to-end reinforcement learning (RL)<n>It introduces lightweight knowledge hypergraph construction, models retrieval as a multi-turn agent-environment interaction.<n>Experiments on standard RAG datasets show that Graph-R1 outperforms traditional GraphRAG and RL-enhanced RAG methods in reasoning accuracy, retrieval efficiency, and generation quality.
  arXiv  Detail & Related papers  (2025-07-29T15:01:26Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on Graphs [58.10503898336799]
  We introduce the RAG-on-Graphs Library (RGL), a modular framework that seamlessly integrates the complete RAG pipeline.<n>RGL addresses key challenges by supporting a variety of graph formats and integrating optimized implementations for essential components.<n>Our evaluations demonstrate that RGL not only accelerates the prototyping process but also enhances the performance and applicability of graph-based RAG systems.
  arXiv  Detail & Related papers  (2025-03-25T03:21:48Z)
• LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration [28.531772644666663]
  We propose LEGO-GraphRAG, a modular framework that enables fine-grained decomposition of the GraphRAG workflow.<n>Our framework facilitates comprehensive empirical studies of GraphRAG on large-scale real-world graphs and diverse query sets.
  arXiv  Detail & Related papers  (2024-11-06T15:32:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.