作者位次 #2/15ACL 2026Findings· Findings of ACL
MM - D oc- R 1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning
Jiahang Lin · Kai Hu · Binghai Wang · Yuhao Zhou · Zhiheng Xi · Honglin Guo · Shichun Liu · Junzhe Wang · Shihan Dou · Enyu Zhou · Hang Yan · Zhenhua Han · Tao Gui · Qi Zhang · Xuanjing Huang
摘要
Conventional Retrieval-Augmented Generation (RAG) systems often struggle with complex multi-hop queries over long documents due to their single-pass retrieval. We introduce MM-Doc-R1 , a novel framework that employs an agentic, vision-aware workflow to address long document visual question answer...