D2-ScaleAgent：面向长文档理解的双维度缩放方法

中文摘要 AI 辅助

多模态检索增强生成（RAG）是针对视觉丰富型长文档理解的关键技术。现有多模态RAG方法正逐步向多智能体系统演进：它们首先基于查询检索相关页面，随后迭代理解这些页面中的信息。然而，这些方法通常依赖固定工作流，且在测试时缺乏动态缩放计算的能力，往往导致证据不足。为解决这一问题，我们提出D2-ScaleAgent，这是一个为检索与推理引入双维度缩放范式的智能体框架。D2-ScaleAgent的核心是基于查询内在难度、以持续更新的证据库（作为智能体的动态工作记忆）为中心、由验证智能体驱动的动态路由循环：当需要扩展检索时，智能体向外路由（检索缩放），将查询分解为属性并执行并行页面检索，随后进行自适应剪枝以确保全面的证据覆盖；当需要细粒度推理时，智能体向内路由（推理缩放），动态选择不同粒度与数量的子智能体从页面中提取证据。最终，D2-ScaleAgent对证据链实现逻辑闭合。大量实验表明，D2-ScaleAgent在MMLongBench-Doc、LongDocURL等长且视觉丰富的文档基准上表现有效。

英文摘要

Multi-modal retrieval-augmented generation (RAG) is a key technique for visually rich long document understanding. Existing multi-modal RAG methods are progressively advancing toward multi-agent systems: they first retrieve relevant pages based on a query, and then iteratively understand information within those pages. However, these methods typically rely on fixed workflows and lack the ability to dynamically scale computation at test time, often leading to insufficient evidence. To address this, we propose D2-ScaleAgent, an agentic framework that introduces a dual-dimensional scaling paradigm for retrieval and reasoning. The core of D2-ScaleAgent is a Verifier agent-driven dynamic routing loop based on the intrinsic difficulty of the query, centered around a continuously updated evidence bank that serves as the agent's dynamic working memory: when retrieval needs to be expanded, the agent routes outward (retrieval scaling), decomposing the query into attributes and performing parallel page retrieval, followed by adaptive pruning to ensure comprehensive evidence coverage. When fine-grained reasoning is required, the agent routes inward (reasoning scaling), dynamically selecting sub-agents with varying granularity and count to extract evidence from pages. Finally, D2-ScaleAgent achieves logical closure over the evidence chain. Extensive experiments demonstrate that D2-ScaleAgent is effective on long and visually rich document benchmarks like MMLongBench-Doc, LongDocURL, etc.

发表机构

• Zhejiang University（浙江大学）
• Alibaba Group（阿里巴巴集团）
• University of Science and Technology of China（中国科学技术大学）

机构由 AI 辅助整理，请以论文原文为准。