{"ID":2886945,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02435","arxiv_id":"2508.02435","title":"Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking","abstract":"Retrieval-augmented generation (RAG) is critical for reducing hallucinations and incorporating external knowledge into Large Language Models (LLMs). However, advanced RAG systems face a trade-off between performance and efficiency. Multi-round RAG approaches achieve strong reasoning but incur excessive LLM calls and token costs, while Graph RAG methods suffer from computationally expensive, error-prone graph construction and retrieval redundancy. To address these challenges, we propose T$^2$RAG, a novel framework that operates on a simple, graph-free knowledge base of atomic triplets. T$^2$RAG leverages an LLM to decompose questions into searchable triplets with placeholders, which it then iteratively resolves by retrieving evidence from the triplet database. Empirical results show that T$^2$RAG significantly outperforms state-of-the-art multi-round and Graph RAG methods, achieving an average performance gain of up to 11\\% across six datasets while reducing retrieval costs by up to 45\\%. Our code is available at https://github.com/rockcor/T2RAG","short_abstract":"Retrieval-augmented generation (RAG) is critical for reducing hallucinations and incorporating external knowledge into Large Language Models (LLMs). However, advanced RAG systems face a trade-off between performance and efficiency. Multi-round RAG approaches achieve strong reasoning but incur excessive LLM calls and to...","url_abs":"https://arxiv.org/abs/2508.02435","url_pdf":"https://arxiv.org/pdf/2508.02435v1","authors":"[\"Shengbo Gong\",\"Xianfeng Tang\",\"Carl Yang\",\"Wei jin\"]","published":"2025-08-04T13:50:44Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":611386,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2886945,"paper_url":"https://arxiv.org/abs/2508.02435","paper_title":"Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking","repo_url":"https://github.com/rockcor/T2RAG","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}