Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and Consolidation· 导航稀疏证据：通过显式上下文选择和整合的代理视觉 RAG
Visual Retrieval-Augmented Generation (VRAG) empowers models to navigate and answer queries about visually rich documents by retrieving relevant page images as visual evidence and reasoning over their content. However, effectively utilizing this visual evidence is usually impeded by two main challenges. First, answer-relevant evidence is sparse and may be concentrated in a small region of one page or dispersed across multiple pages. Second, existing agentic methods often generate answers based on raw exploration trajectories or compressed textual memories rather than an explicitly organized set of supporting images, making answers susceptible to exploration noise and obscuring the evidence-backed reasoning trace. We argue that the bottleneck lies not only in evidence discovery but also in
解决视觉证据稀疏与分散问题，提升 VRAG 模型的证据利用效率。
- 核心方法
- 提出代理视觉 RAG 方法，通过显式上下文选择和整合支持图像来改善答案生成过程。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 视觉证据稀疏且分散，现有方法难以有效利用视觉证据生成准确答案。
- 关键实验
- 未提供具体实验数据，但展示了模型在多个视觉文档查询任务上的改进。
- 主要贡献
- 提高了基于视觉证据的答案生成质量和可解释性，减少了探索噪声的影响。
- 意义与局限
- 该方法在处理视觉丰富文档查询时具有重要意义，但可能在复杂多变的视觉环境中遇到局限。