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 T²RAG, a novel framework that operates on a simple, graph-free knowledge base of atomic triplets. T²RAG 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 T²RAG 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%.