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

翻译：检索增强生成（RAG）对于减少大语言模型（LLM）的幻觉并融入外部知识至关重要。然而，高级RAG系统在性能与效率之间面临权衡。多轮RAG方法虽能实现强推理能力，但会引发过多的LLM调用和令牌成本；而图RAG方法则受限于计算昂贵、易出错的图构建过程及检索冗余。为解决这些问题，我们提出T$^2$RAG——一个基于无图结构的原子三元组知识库的新型框架。T$^2$RAG利用LLM将问题分解为带占位符的可搜索三元组，并通过从三元组数据库中检索证据进行迭代求解。实验结果表明，T$^2$RAG显著优于最先进的多轮与图RAG方法，在六个数据集上平均性能提升最高达11%，同时检索成本降低最多45%。我们的代码开源在https://github.com/rockcor/T2RAG