{"ID":6537427,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11683","arxiv_id":"2607.11683","title":"RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM","abstract":"Graph retrieval-augmented generation (GraphRAG) enhances large language models with structured knowledge, yet existing systems construct knowledge graphs in a single extraction pass, producing noisy entities and brittle retrieval. RAGU, an open-source modular GraphRAG engine, addresses this by separating extraction from consolidation: entities and relations pass through two-stage typed extraction, DBSCAN-backed deduplication, LLM summarization, and Leiden community detection. A key insight motivates a compact extractor: the skills an in-pipeline LLM needs - comprehension, extraction, reasoning over context - are language skills that grow only weakly with model size, unlike factual world knowledge. Accordingly, we train Meno-Lite-0.1, a 7B model optimized for language skills, which outperforms Qwen2.5-32B on knowledge-graph construction (+12.5% relative harmonic mean) and matches it on English GraphRAG tasks. On GraphRAG-Bench (Medical), RAGU retrieves the most complete context at every factoid level (evidence recall up to 0.84 vs. $\\leq$0.76) and overtakes HippoRAG2 on synthesis tasks; on multi-hop factoid QA, the apparent HippoRAG2 advantage is shown to be largely an answer-format artifact. RAGU is installable via $\\texttt{pip install graph_ragu}$, runs on a single GPU, and is released under MIT. The source code is publicly available at https://github.com/RaguTeam/RAGU, and the Meno-Lite-0.1 model can be obtained from https://huggingface.co/bond005/meno-lite-0.1.","short_abstract":"Graph retrieval-augmented generation (GraphRAG) enhances large language models with structured knowledge, yet existing systems construct knowledge graphs in a single extraction pass, producing noisy entities and brittle retrieval. RAGU, an open-source modular GraphRAG engine, addresses this by separating extraction fro...","url_abs":"https://arxiv.org/abs/2607.11683","url_pdf":"https://arxiv.org/pdf/2607.11683v1","authors":"[\"Mikhail Komarov\",\"Ivan Bondarenko\",\"Stanislav Shtuka\",\"Oleg Sedukhin\",\"Roman Shuvalov\",\"Yana Dementyeva\",\"Matvey Solovyov\",\"Nikolay O. Nikitin\"]","published":"2026-07-13T15:20:51Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":614199,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-14T02:54:43.516908796Z","DeletedAt":null,"paper_id":6537427,"paper_url":"https://arxiv.org/abs/2607.11683","paper_title":"RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM","repo_url":"https://github.com/RaguTeam/RAGU","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}