Retrieval-Augmented Generation (RAG) has demonstrated significant effectiveness in enhancing large language models (LLMs) for complex multi-hop question answering (QA). For multi-hop QA tasks, current iterative approaches predominantly rely on LLMs to self-guide and plan multi-step exploration paths during retrieval, leading to substantial challenges in maintaining reasoning coherence across steps from inaccurate query decomposition and error propagation. To address these issues, we introduce Reasoning Tree Guided RAG (RT-RAG), a novel hierarchical framework for complex multi-hop QA. RT-RAG systematically decomposes multi-hop questions into explicit reasoning trees, minimizing inaccurate decomposition through structured entity analysis and consensus-based tree selection that clearly separates core queries, known entities, and unknown entities. Subsequently, a bottom-up traversal strategy employs iterative query rewriting and refinement to collect high-quality evidence, thereby mitigating error propagation. Comprehensive experiments show that RT-RAG substantially outperforms state-of-the-art methods by 7.0% F1 and 6.0% EM, demonstrating the effectiveness of RT-RAG in complex multi-hop QA.

翻译：检索增强生成（RAG）在增强大语言模型（LLM）处理复杂多跳问答（QA）任务方面已展现出显著成效。针对多跳问答任务，现有的迭代方法主要依赖LLM在检索过程中自我引导并规划多步探索路径，这导致因查询分解不准确和错误传播而在跨步骤间保持推理连贯性方面面临巨大挑战。为解决这些问题，我们提出了推理树引导的RAG（RT-RAG），一种用于复杂多跳问答的新型分层框架。RT-RAG通过结构化实体分析和基于共识的树选择，将多跳问题系统性地分解为显式推理树，从而清晰分离核心查询、已知实体和未知实体，最大限度地减少不准确分解。随后，采用自底向上的遍历策略，通过迭代式查询重写与精化来收集高质量证据，从而缓解错误传播。综合实验表明，RT-RAG在F1分数和EM分数上分别大幅超越现有最优方法7.0%和6.0%，证明了其在复杂多跳问答中的有效性。