{"ID":2864892,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21710","arxiv_id":"2509.21710","title":"Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval","abstract":"Graph-based Retrieval-Augmented Generation (GraphRAG) has become the important paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing approaches are constrained by their reliance on high-quality knowledge graphs: manually built ones are not scalable, while automatically extracted ones are limited by the performance of LLM extractors, especially when using smaller, local-deployed models. To address this, we introduce Think-on-Graph 3.0 (ToG-3), a novel framework featuring a Multi-Agent Context Evolution and Retrieval (MACER) mechanism. Its core contribution is the dynamic construction and iterative refinement of a Chunk-Triplets-Community heterogeneous graph index, powered by a Dual-Evolution process that adaptively evolves both the query and the retrieved sub-graph during reasoning. ToG-3 dynamically builds a targeted graph index tailored to the query, enabling precise evidence retrieval and reasoning even with lightweight LLMs. Extensive experiments demonstrate that ToG-3 outperforms compared baselines on both deep and broad reasoning benchmarks, and ablation studies confirm the efficacy of the components of MACER framework. The source code are available in https://github.com/DataArcTech/ToG-3.","short_abstract":"Graph-based Retrieval-Augmented Generation (GraphRAG) has become the important paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing approaches are constrained by their reliance on high-quality knowledge graphs: manually built ones are not scalable, while automatically extracted...","url_abs":"https://arxiv.org/abs/2509.21710","url_pdf":"https://arxiv.org/pdf/2509.21710v2","authors":"[\"Xiaojun Wu\",\"Cehao Yang\",\"Xueyuan Lin\",\"Chengjin Xu\",\"Xuhui Jiang\",\"Yuanliang Sun\",\"Hui Xiong\",\"Jia Li\",\"Jian Guo\"]","published":"2025-09-26T00:13:10Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":609210,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2864892,"paper_url":"https://arxiv.org/abs/2509.21710","paper_title":"Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval","repo_url":"https://github.com/DataArcTech/ToG-3","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}