用分文档代理协作提升长文档问答准确率
SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation
- 每个文档由专属代理处理，再由协调器整合答案
- 在LOONG基准上达58.1分，比普通RAG高25分
- 节省62%成本，适合大规模多文档问答场景
回答复杂现实问题常需整合海量文档中的零散事实。标准RAG存在证据覆盖不全问题，而长上下文大模型在处理海量输入时推理不可靠。本文提出SPD-RAG，一种分层多代理框架，沿文档维度分解问题。每个文档由专用文档级代理独立处理，实现精准检索；协调器调度相关代理并聚合部分答案。通过受限标记的合成层（支持递归映射-归约）合并输出，实现跨文档信息融合。该文档级专业化与集中式融合策略，在异构多文档场景中提升了可扩展性与答案质量，同时构建了模块化、可扩展的检索管道。在针对长上下文多文档问答的LOONG基准（EMNLP 2024）测试中，SPD-RAG获得58.1分（GPT-5评估），优于普通RAG（33.0）和代理式RAG（32.8），且仅消耗全上下文基线68.0分方案38%的API成本。
原文摘要 · Abstract (English)
Answering complex, real-world queries often requires synthesizing facts scattered across vast document corpora. In these settings, standard retrieval-augmented generation (RAG) pipelines suffer from incomplete evidence coverage, while long-context large language models (LLMs) struggle to reason reliably over massive inputs. We introduce SPD-RAG, a hierarchical multi-agent framework for exhaustive cross-document question answering that decomposes the problem along the document axis. Each document is processed by a dedicated document-level agent operating only on its own content, enabling focused retrieval, while a coordinator dispatches tasks to relevant agents and aggregates their partial answers. Agent outputs are synthesized by merging partial answers through a token-bounded synthesis layer (which supports recursive map-reduce for massive corpora). This document-level specialization with centralized fusion improves scalability and answer quality in heterogeneous multidocument settings while yielding a modular, extensible retrieval pipeline. On the LOONG benchmark (EMNLP 2024) for long-context multi-document QA, SPD-RAG achieves an Avg Score of 58.1 (GPT-5 evaluation), outperforming Normal RAG (33.0) and Agentic RAG (32.8) while using only 38% of the API cost of a full-context baseline (68.0).
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。