基于强化学习的高效可迁移智能知识图谱检索增强生成
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
AI总结：
提出KG-R1框架，通过强化学习将单个智能体与知识图谱交互，统一检索、推理和生成过程，在KGQA基准上以更少生成token提升准确率，并展现跨图谱的零样本迁移能力。
摘要：
知识图谱检索增强生成（KG-RAG）将大型语言模型（LLMs）与结构化、可验证的知识图谱（KGs）相结合，以减少幻觉并提供推理轨迹。然而，当前的KG-RAG系统通常依赖于多个LLM模块（如规划、推理和响应）的固定流水线，这增加了推理成本，并将性能与特定图模式绑定。为了解决这个问题，我们引入了KG-R1，一个通过强化学习（RL）优化KG-RAG的智能体框架。与模块化工作流不同，KG-R1使用单个智能体，将KGs作为其环境进行交互，学习在每一步检索信息，并将其融入统一的推理和生成过程中。在知识图谱问答（KGQA）基准测试中，KG-R1展示了高效性和可迁移性——使用Qwen 2.5-3B，KG-R1以比先前使用更大基础或微调模型的多模块工作流方法更少的生成token提高了答案准确性。此外，KG-R1表现出强大的即插即用能力：训练后，无需重新训练即可在未见过的KGs上保持准确性。这些特性使KG-R1成为实际部署中很有前景的KG-RAG框架。我们的代码公开在github.com/junhongmit/KG-R1/。
英文摘要：
Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucination and provide reasoning traces. However, current KG-RAG systems often rely on fixed pipelines of multiple LLM modules (e.g., planning, reasoning, and responding), which inflate inference costs and tie performance to specific graph schemas. To address this, we introduce KG-R1, an agentic framework that optimizes KG-RAG through reinforcement learning (RL). Unlike modular workflows, KG-R1 uses a single agent that interacts with KGs as its environment, learning to retrieve information at each step and incorporating it into its reasoning and generation in a unified process. Across Knowledge-Graph Question Answering (KGQA) benchmarks, KG-R1 demonstrates both efficiency and transferability-using Qwen 2.5-3B, KG-R1 improves answer accuracy with fewer generation tokens than prior multi-module workflow methods that use much larger foundation or fine-tuned models. Furthermore, KG-R1 exhibits strong plug-and-play capability: after training, maintaining accuracy on unseen KGs without retraining. These properties make KG-R1 a promising KG-RAG framework for real-world deployment. Our code is publicly available at github.com/junhongmit/KG-R1/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
