用强化学习动态调度模型，让问答系统更省钱又高效。
GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning
- 通过分层路由选择不同规模的图检索与生成模型
- 减少大模型使用率近30%，多跳问答准确率领先
- 适合追求低成本高效率知识问答系统的开发者
基于图的检索增强生成（GraphRAG）已成为知识密集型问答的重要范式，尤其适用于需结构化证据组织和多跳推理的任务。然而，现有GraphRAG系统通常采用统一固定架构，依赖单一且昂贵的大规模生成语言模型（LLM）处理所有查询，难以适应问题复杂度差异，导致计算资源浪费。为此，我们提出GraphRAG-Router，一种成本高效的框架，采用分层路由策略协调异构GraphRAG与生成器LLM。该框架先通过监督微调预热，再经两阶段强化学习优化，第二阶段引入课程式成本感知奖励，鼓励根据问题难度智能分配生成器。在六个通用领域与多跳问答基准上的实验表明，GraphRAG-Router持续优于现有先进基线，在保持强泛化能力的同时，将大模型过量使用降低近30%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。