Retrieval-augmented generation (RAG) remains brittle on multi-step questions and heterogeneous evidence sources, trading accuracy against latency and token/tool budgets. This paper introducesHierarchical Sequence (HSEQ) Iteration for Heterogeneous Question Answering, a unified framework 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, HSEQ 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) 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)在处理多步问题和异构证据源时依然脆弱,需要在准确性、延迟以及令牌/工具预算之间进行权衡。本文提出了用于异构问答的层次化序列(HSEQ)迭代框架,这是一个统一的框架,它(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层次化序列,以及(ii)执行结构感知的迭代,以在答案合成前收集恰好足够的证据。一个头部智能体提供指导以引导检索,而一个迭代智能体通过尊重结构的操作(例如,父/子节点跳转、表格行/列邻居、KG关系)来选择和扩展HSeq;最后,头部智能体将规范化的证据组合起来以生成最终答案,并可选择通过一个精炼循环来解决检测到的矛盾。在HotpotQA(文本)、HybridQA/TAT-QA(表格+文本)和MetaQA(KG)上的实验表明,相较于强大的单次检索、多跳以及智能体式RAG基线方法,本框架在保持高效率的同时,在EM/F1指标上取得了持续提升。此外,HSEQ展现出三个关键优势:(1)格式无关的统一性,使得单一策略能够跨文本、表格和KG操作,无需针对每个数据集进行专门化;(2)有指导的、预算感知的迭代,在保持准确性的同时减少了不必要的跳转、工具调用和令牌消耗;以及(3)证据规范化以实现可靠的问答,提高了答案的一致性和可审计性。