发表机构
Peking University; Panasonic Connect Co., Ltd.（北京大学; 松下连接株式会社）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有多模态RAG存在的视觉引用不准或与答案脱节问题，本文提出MCite-RL框架，通过智能体优化模块和引用增强型奖励机制实现引用精度与答案质量的联合优化，经多基准实验验证有效。
AI 中文摘要
带有视觉引用的多模态检索增强生成（RAG）对于确保多模态大语言模型（MLLM）的可追溯性和可验证性至关重要。然而，当前的RAG和基于监督微调（SFT）的方法难以实现稳健的跨模态推理，导致视觉引用不准确或引用与生成答案脱节。为解决这些局限，本文提出MCite-RL，一种专为可靠多模态RAG设计的引用增强型智能体强化学习框架。MCite-RL引入用于视觉引用的智能体优化模块，该模块采用迭代检索、推理和递归裁剪逐步缩小搜索空间，将引用转变为动态、证据驱动的推理过程而非静态步骤。此外，本文融入引用增强型奖励机制，在强化学习范式中整合过程级和结果级反馈，共同优化答案准确性和来源可追溯性。在Wiki-VISA、FinRAGBench-V和MMLongBench-Doc等基准上开展的大量实验表明，MCite-RL可有效实现引用精度与答案质量的联合优化。
英文摘要
Multimodal Retrieval-Augmented Generation (RAG) with visual citation is crucial for ensuring the traceability and verifiability of MLLMs. However, current RAG and SFT-based methods struggle to achieve robust cross-modal reasoning, causing imprecise visual citations or decoupling between the citation and the generated answers. To address these limitations, we propose MCite-RL, a citation-enhanced agentic reinforcement learning framework designed for reliable multimodal RAG. MCite-RL introduces an Agentic Refinement module for visual citation that employs iterative retrieval, reasoning, and recursive cropping to progressively narrow the search space, transforming citation into a dynamic, evidence-driven reasoning process rather than a static step. Furthermore, we incorporate a Citation-enhanced Reward mechanism that integrates both process-level and outcome-level feedback within a reinforcement learning paradigm to jointly optimize answer accuracy and source traceability. Extensive experiments on benchmarks such as Wiki-VISA, FinRAGBench-V, and MMLongBench-Doc demonstrate that MCite-RL effectively achieves the joint optimization of citation precision and answer quality.
