{"id":"2607.24748","title":"VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents","url":"https://codeofpaper.com/paper/2607.24748","arxiv_url":"https://arxiv.org/abs/2607.24748","published":"2026-05-21","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}