MARDoc：面向多模态长文档问答的记忆感知精炼智能体框架
MARDoc: A Memory-Aware Refinement Agent Framework for Multimodal Long Document QA
AI总结：
提出MARDoc框架，通过解耦为探索、精炼和反思三个智能体，并利用结构化记忆替代完整交互历史，减少上下文噪声，提升多模态长文档问答性能。
摘要：
迭代检索-推理智能体近期在多模态长文档问答中展现出潜力。然而，现有系统大多维护一个不断增长的单一上下文，混合了检索轨迹、观察和中间推理。随着交互积累，关键证据变得分散和稀释，使多跳推理变得嘈杂。我们提出MARDoc，一个记忆感知精炼智能体框架，将长文档问答解耦为三个专门智能体：探索者负责多粒度多模态检索，精炼者负责将交互轨迹蒸馏为结构化证据和推理记忆，反思者负责检查证据充分性并提供针对性反馈。在迭代过程中，智能体依赖动态更新的结构化记忆，而非完整的累积交互历史。这种设计减少了上下文噪声，同时保留了答案关键事实及其逻辑依赖。在MMLongBench-Doc和DocBench上的实验表明，MARDoc取得了强劲结果，优于同骨干基线，并证明了结构化记忆在智能体文档问答中的有效性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
