Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and Consolidation

The paper introduces SCoRE, an agentic framework for Visual Retrieval-Augmented Generation that explicitly selects and consolidates visual evidence before generating answers. It addresses two key challenges: sparse, scattered evidence and noisy exploration trajectories that obscure reasoning. By maintaining a textual ledger of relevant observations and reloading original images for a logical evidence sequence, SCoRE decouples reasoning from exploration and enforces strict visual grounding, with training that rewards evidence coverage, compactness, and answer correctness.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• rag
• agents
• reinforcement-learning
• efficiency