MCite-RL: Towards Reliable Multimodal RAG via Citation-enhanced Agentic Reinforcement Learning

2026-08-22

AI Summary

为解决多模态RAG中视觉引用不准确及与生成答案脱节问题，提出MCite-RL框架，通过代理精炼模块和增强奖励机制提高引用精确度和答案质量。

Abstract

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.

Problem

• Multimodal RAG
• cross-modal reasoning
• visual citation
• answer accuracy
• source traceability

Innovation

• Agentic Refinement
• Citation-enhanced Reward
• Multimodal RAG