基于树结构的RAG框架：通过自适应规划和拓扑感知证据收集实现高证据密度问答
A Tree-based RAG Framework for Evidence-Intensive QA via Adaptive Planning and Topology-Aware Evidence Gathering
- Korea University（高丽大学）
- Hanyang University（汉阳大学）
- Hyundai Motor Company（现代汽车公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文针对高证据密度问答场景下现有结构化RAG方法的结构僵化与证据收集缺陷，提出APT-RAG框架，通过自适应规划、拓扑感知证据收集及证据引导批量生成实现性能提升。
AI中文摘要：
近期的结构化RAG方法利用树或图结构的推理结构来改进多跳问答，但在高证据密度问答场景中存在关键局限：回答问题需综合数十甚至数百篇分散文档的信息，这类场景下现有方法存在结构僵化问题，限制了自适应推理扩展；以及证据收集未考虑拓扑结构，无法有效整合不同推理节点的证据。为解决这些问题，本文提出APT-RAG框架，即自适应规划与拓扑感知证据收集的RAG框架。其中自适应规划可基于问题依赖关系和证据需求动态扩展推理结构；拓扑感知证据收集通过复用兄弟节点证据、直接检索、聚合子节点证据提升证据覆盖率。本文还引入证据引导的批量答案生成，以降低高证据密度问答中的显著生成开销。在高证据密度问答基准测试中，APT-RAG的性能优于现有结构化RAG方法，代码可在指定网址获取。
英文摘要：
Recent structured RAG methods leverage tree- or graph-based reasoning structures to improve multi-hop QA. However, they face key limitations in evidence-intensive QA, where answering a question requires synthesizing information scattered across dozens or even hundreds of documents: structural rigidity, which limits adaptive reasoning expansion, and topology-ignorant evidence gathering, which prevents effective integration of evidence across different reasoning nodes. To address these issues, we propose APT-RAG, an Adaptive Planning and Topology-aware evidence gathering RAG framework. Adaptive planning dynamically expands the reasoning structure based on question dependencies and evidence requirements, while topology-aware evidence gathering improves evidence coverage through sibling evidence reuse, direct retrieval, and evidence aggregation from child nodes. We further introduce evidence-guided batched answer generation to reduce significant generation overhead in evidence-intensive QA. In the experiments on evidence-intensive QA benchmarks, APT-RAG outperforms existing structured RAG methods. Our code is available at https://github.com/hyudsl/APT-RAG.
