Preprint
Aug 2026
AWM: Answerable Working Memory for Long-Document VQA Agents
Long-document visual question answering increasingly relies on VLM agents that retrieve candidate pages, inspect page images, write findings to working memory, and synthesize answers. Working memory should carry answer-supporting evidence across page inspections for later grounded answering, yet existing evaluation mai...
Dongzhuoran Zhou, Yuqicheng Zhu, Yu-Le Liu et al.
· 3 citations
· ⚡1