RELOOP：基于多跳推理与规划器的异构问答递归检索
RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA
AI总结：
RELOOP通过递归检索和结构感知迭代，提升多步问题和异构证据源的问答准确性，实现高效率的证据收集与答案生成。
摘要：
检索增强生成（RAG）在多步问题和异构证据源上存在脆弱性，牺牲了准确率以换取延迟和令牌预算。本文提出RELOOP框架，利用分层序列（HSEQ）将文档、表格和知识图谱线性化为可逆的分层序列，并通过结构感知迭代收集足够的证据。头部代理提供指导以引导检索，迭代代理通过结构尊重的操作（如父/子跳转、表格行/列邻居、KG关系）选择和扩展HSeq。最终头部代理将标准化的证据组合生成最终答案，并通过可选的精炼循环解决检测到的矛盾。在HotpotQA（文本）、HybridQA/TAT-QA（表格+文本）和MetaQA（KG）上的实验表明，RELOOP在准确率和效率上优于强单次、多跳和代理RAG基线。此外，RELOOP具有三个关键优势：（1）格式无关的统一性，使单一策略能跨文本、表格和KG运行；（2）指导性的预算感知迭代，减少不必要的跳转、工具调用和令牌消耗；（3）证据标准化以提高问答的可靠性，提升答案的一致性和可审计性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
