EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation

2026-04-16

AI Summary

This work addresses the limitations of existing knowledge graph–augmented retrieval-augmented generation (KG-RAG) methods, which struggle to adapt to the dynamic demands of downstream tasks and fail to effectively filter out low-contribution knowledge. To overcome these challenges, the authors propose EvoRAG, a novel framework that establishes, for the first time, a closed-loop self-evolution mechanism linking user feedback, large language models, and knowledge graphs. EvoRAG propagates response-level user feedback back through multi-hop retrieval paths and quantifies the contribution of individual triples, enabling fine-grained, task-adaptive dynamic refinement of the knowledge graph. Experimental results demonstrate that EvoRAG surpasses the current state-of-the-art KG-RAG approaches by 7.34% in reasoning accuracy, significantly enhancing system performance and robustness in real-world scenarios.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Knowledge Acquisition
• Machine Learning: Evolutionary Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

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.

Problem

• Knowledge Graph-based RAG
• feedback-driven adaptation
• triplet-level contribution
• task-specific knowledge refinement
• reasoning accuracy

Innovation

• feedback-driven backpropagation
• self-evolving KG-RAG
• triplet-level contribution
• knowledge graph refinement
• adaptive reasoning