Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) has emerged as a promising paradigm for enhancing LLM reasoning by retrieving multi-hop paths from KGs. However, existing KG-RAG frameworks often underperform in real-world scenarios because the pre-captured knowledge dependencies are not tailored to the downstream task or its evolving requirements. These frameworks struggle to adapt to task-specific requirements and lack mechanisms to filter low-contribution knowledge during generation. We observe that feedback on generated responses offers effective supervision for improving KG quality, as it directly reflects user expectations and provides insights into the correctness and usefulness of the output. However, a key challenge lies in effectively linking response-level feedback to triplet-level contribution evaluation and knowledge updates in the KG. In this work, we propose EvoRAG, a self-evolving KG-RAG framework that leverages the feedback over generated responses to continuously refine the KG and enhance reasoning accuracy. EvoRAG introduces a feedback-driven backpropagation mechanism that attributes feedback to retrieved paths by measuring their utility for response and propagates this utility back to individual triplets, supporting fine-grained KG refinements towards more adaptive and accurate reasoning. Through EvoRAG, we establish a closed loop that couples feedback, LLM, and graph data, continuously enhancing the performance and robustness in real-world scenarios. Experimental results show that EvoRAG improves reasoning accuracy by $7.34\%$ over state-of-the-art KG-RAG frameworks. The source code has been made available at https://github.com/iDC-NEU/EvoRAG.

翻译：基于知识图谱的检索增强生成（KG-RAG）已成为通过从知识图谱中检索多跳路径来增强大语言模型推理能力的一种有前景的范式。然而，现有的KG-RAG框架在实际场景中往往表现不佳，原因是预先捕获的知识依赖关系并未针对下游任务或其动态需求进行定制。这些框架难以适应任务特定需求，且缺乏在生成过程中过滤低贡献知识的机制。我们观察到，对生成响应的反馈为改进知识图谱质量提供了有效监督，因为它直接反映了用户期望，并揭示了输出的正确性和有用性。然而，一个关键挑战在于如何有效将响应级反馈关联到三元组级贡献评估及知识图谱中的知识更新。在本工作中，我们提出EvoRAG——一种自我演化的KG-RAG框架，它利用对生成响应的反馈持续优化知识图谱并提升推理准确性。EvoRAG引入了一种反馈驱动的反向传播机制，通过衡量检索路径对响应的效用将反馈归因于这些路径，并将该效用反向传播至单个三元组，从而支持细粒度的知识图谱优化，以实现更具适应性和准确性的推理。通过EvoRAG，我们建立了一个耦合反馈、大语言模型和图数据的闭环，持续提升实际场景中的性能与鲁棒性。实验结果表明，EvoRAG的推理准确率相比最先进的KG-RAG框架提升了7.34%。源代码已公开于https://github.com/iDC-NEU/EvoRAG。