Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval

TL;DR

This paper surveys the current state and future challenges of Visual Document Retrieval (VDR) in the era of Multimodal Large Language Models, highlighting methodological advances, benchmark landscapes, and future research directions.

Contribution

It provides the first comprehensive survey of VDR approaches, categorizes recent methodologies, and outlines future research directions in multimodal document intelligence.

Findings

Categorized approaches into embedding, reranker, and RAG/Agentic models.

Analyzed benchmark datasets and evaluation metrics.

Identified key challenges and promising future research areas.

Abstract

With the rapid proliferation of multimodal information, Visual Document Retrieval (VDR) has emerged as a critical frontier in bridging the gap between unstructured visually rich data and precise information acquisition. Unlike traditional natural image retrieval, visual documents exhibit unique characteristics defined by dense textual content, intricate layouts, and fine-grained semantic dependencies. This paper presents the first comprehensive survey of the VDR landscape, specifically through the lens of the Multimodal Large Language Model (MLLM) era. We begin by examining the benchmark landscape, and subsequently dive into the methodological evolution, categorizing approaches into three primary aspects: multimodal embedding models, multimodal reranker models, and the integration of Retrieval-Augmented Generation (RAG) and Agentic systems for complex document intelligence. Finally, we identify persistent challenges and outline promising future directions, aiming to provide a clear roadmap for future multimodal document intelligence.