用分角色协作的结构化记忆提升长文档多模态问答准确率
MARDoc: A Memory-Aware Refinement Agent Framework for Multimodal Long Document QA
- 分三角色：探索者、提炼者、反思者，分别负责检索、提炼证据和检查逻辑
- 相比传统累积对话历史，结构化记忆让关键信息更清晰，多跳推理更稳定
- 在两个基准测试上超越同类模型，适合需要精准长文理解的场景
迭代式检索-推理智能体在多模态长文档问答中展现出潜力。然而，现有系统通常维护单一不断增长的上下文，混合了检索轨迹、观察结果和中间推理，导致关键证据分散稀释，多跳推理噪声大。我们提出MARDoc，一种面向长文档问答的内存感知精炼代理框架，将任务拆分为三个专业代理：探索者负责多粒度多模态检索，提炼者将交互轨迹提炼为结构化证据与推理记忆，反思者检查证据充分性并提供针对性反馈。各轮迭代中，代理依赖动态更新的结构化记忆，而非完整累积的历史记录。该设计在减少上下文噪声的同时保留答案相关事实及其逻辑依赖。在MMLongBench-Doc和DocBench上的实验表明，MARDoc表现优异，优于同主干基线模型，验证了结构化记忆在智能体文档问答中的有效性。
原文摘要 · Abstract (English)
Iterative retrieval-reasoning agents have recently shown promise for multimodal long-document question answering. However, most existing systems maintain a single growing context that mixes retrieval traces, observations, and intermediate reasoning. As interactions accumulate, key evidence becomes scattered and diluted, making multi-hop reasoning noisy. We propose MARDoc, a Memory-Aware Refinement Agent framework that decouples long-document QA into three specialized agents: an Explorer for multi-granularity multimodal retrieval, a Refiner for distilling interaction traces into structured evidence and reasoning memories, and a Reflector for checking evidence sufficiency and providing targeted feedback. Across iterations, the agents rely on a dynamically updated structured memory rather than a full accumulated interaction history. This design reduces context noise while preserving answer-critical facts and their logical dependencies. Experiments on MMLongBench-Doc and DocBench show that MARDoc achieves strong results, outperforming same-backbone baselines and demonstrating the effectiveness of structured memory for agentic document QA.
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。