{"ID":2882605,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.09460","arxiv_id":"2508.09460","title":"Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented Generation","abstract":"Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) significantly enhances the reasoning capabilities of LargeLanguage Models by leveraging structured knowledge. However, existing KG-RAG frameworks typically operate as open-loop systems, suffering from cognitive blindness, an inability to recognize their exploration deficiencies. This leads to relevance drift and incomplete evidence, which existing self-refinement methods, designed for unstructured text-based RAG, cannot effectively resolve due to the path-dependent nature of graph exploration. To address this challenge, we propose Metacognitive Knowledge Graph Retrieval Augmented Generation (MetaKGRAG), a novel framework inspired by the human metacognition process, which introduces a Perceive-Evaluate-Adjust cycle to enable path-aware, closed-loop refinement. This cycle empowers the system to self-assess exploration quality, identify deficiencies in coverage or relevance, and perform trajectory-connected corrections from precise pivot points. Extensive experiments across five datasets in the medical, legal, and commonsense reasoning domains demonstrate that MetaKGRAG consistently outperforms strong KG-RAG and self-refinement baselines. Our results validate the superiority of our approach and highlight the critical need for path-aware refinement in structured knowledge retrieval.","short_abstract":"Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) significantly enhances the reasoning capabilities of LargeLanguage Models by leveraging structured knowledge. However, existing KG-RAG frameworks typically operate as open-loop systems, suffering from cognitive blindness, an inability to recognize their expl...","url_abs":"https://arxiv.org/abs/2508.09460","url_pdf":"https://arxiv.org/pdf/2508.09460v1","authors":"[\"Xujie Yuan\",\"Shimin Di\",\"Jielong Tang\",\"Libin Zheng\",\"Jian Yin\"]","published":"2025-08-13T03:35:32Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"RAG\",\"Language Model\",\"LoRA\"]","has_code":false}