提出拓扑感知文档分块框架，提升检索生成效果
TopoChunker: Topology-Aware Agentic Document Chunking Framework
- 用双代理架构构建结构化中间表示，保留段落间依赖关系
- 在GutenQA和GovReport上生成准确率提升8.0%，召回率83.26%
- 减少23.5%的令牌开销，适合复杂文档的结构化处理
当前用于检索增强生成（RAG）的文档分块方法通常将文本线性化，这种强制线性化会破坏固有的拓扑层次结构，导致语义碎片化，降低下游检索质量。本文提出TopoChunker，一种代理式框架，将异构文档映射到结构化中间表示（SIR），以显式保留跨段依赖。为平衡结构保真度与计算成本，TopoChunker采用双代理架构：检查代理动态选择成本优化的提取路径，重构代理执行容量审计与拓扑上下文消歧，重建层级谱系。在非结构化叙事（GutenQA）和复杂报告（GovReport）上的评估显示，该方法性能达到当前最优，在最强的LLM基线基础上生成准确率提升8.0%，召回率@3达83.26%，同时减少23.5%的令牌开销，提供了一种可扩展的结构感知RAG方案。
原文摘要 · Abstract (English)
Current document chunking methods for Retrieval-Augmented Generation (RAG) typically linearize text. This forced linearization strips away intrinsic topological hierarchies, creating ``semantic fragmentation'' that degrades downstream retrieval quality. In this paper, we propose TopoChunker, an agentic framework that maps heterogeneous documents onto a Structured Intermediate Representation (SIR) to explicitly preserve cross-segment dependencies. To balance structural fidelity with computational cost, TopoChunker employs a dual-agent architecture. An Inspector Agent dynamically routes documents through cost-optimized extraction paths, while a Refiner Agent performs capacity auditing and topological context disambiguation to reconstruct hierarchical lineage. Evaluated on unstructured narratives (GutenQA) and complex reports (GovReport), TopoChunker demonstrates state-of-the-art performance. It outperforms the strongest LLM-based baseline by 8.0% in absolute generation accuracy and achieves an 83.26% Recall@3, while simultaneously reducing token overhead by 23.5%, offering a scalable approach for structure-aware RAG.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。