04:00
2026-07-29
machinebrief.com
artificial-intelligence
VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents
Researchers present VLD-RAG, an agentic multimodal retrieval-augmented generation framework for question answering over visually-rich long documents, achieving improved evidence-page retrieval and end…