Retrieval-augmented generation (RAG) remains brittle on multi-step questions and heterogeneous evidence sources, trading accuracy against latency and token/tool budgets. This paper introduces RELOOP, a structure aware framework using Hierarchical Sequence (HSEQ) that (i) linearize documents, tables, and knowledge graphs into a reversible hierarchical sequence with lightweight structural tags, and (ii) perform structure-aware iteration to collect just-enough evidence before answer synthesis. A Head Agent provides guidance that leads retrieval, while an Iteration Agent selects and expands HSeq via structure-respecting actions (e.g., parent/child hops, table row/column neighbors, KG relations); Finally the head agent composes canonicalized evidence to genearte the final answer, with an optional refinement loop to resolve detected contradictions. Experiments on HotpotQA (text), HybridQA/TAT-QA (table+text), and MetaQA (KG) show consistent EM/F1 gains over strong single-pass, multi-hop, and agentic RAG baselines with high efficiency. Besides, RELOOP exhibits three key advantages: (1) a format-agnostic unification that enables a single policy to operate across text, tables, and KGs without per-dataset specialization; (2) \textbf{guided, budget-aware iteration} that reduces unnecessary hops, tool calls, and tokens while preserving accuracy; and (3) evidence canonicalization for reliable QA, improving answers consistency and auditability.

翻译：检索增强生成（RAG）在处理多步问题及异构证据源时仍显脆弱，需在准确性、延迟以及令牌/工具预算之间进行权衡。本文提出RELOOP，一种基于分层序列（HSEQ）的结构感知框架，其（i）将文档、表格和知识图谱线性化为带有轻量级结构标签的可逆分层序列，（ii）在答案合成前执行结构感知迭代以收集恰好足够的证据。头部智能体提供指导以引导检索，而迭代智能体通过尊重结构的操作（如父/子节点跳转、表格行/列邻接、知识图谱关系）选择并扩展HSeq；最终，头部智能体将规范化证据组合以生成最终答案，并可通过可选的优化循环解决检测到的矛盾。在HotpotQA（文本）、HybridQA/TAT-QA（表格+文本）和MetaQA（知识图谱）上的实验表明，相较于强力的单次检索、多跳及智能体式RAG基线方法，RELOOP在保持高效的同时实现了EM/F1指标的持续提升。此外，RELOOP展现出三大关键优势：（1）格式无关的统一性，使得单一策略能够跨文本、表格和知识图谱运行，无需针对各数据集专门调整；（2）**具备引导性且预算感知的迭代机制**，在保持准确性的同时减少了不必要的跳转、工具调用及令牌消耗；（3）证据规范化提升了问答的可靠性，增强了答案的一致性与可审计性。