SOURCE-LINKED INTELLIGENCE

AWM: Answerable Working Memory for Long-Document VQA Agents

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

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 mainly checks final-answer correctness and evidence-page access. This creates a memory-quality blind spot: an agent may reach the right page and answer correctly while leaving behind memory too generic or incomplete to support answering once page context is removed. We introduce \em

Read original source ↗ Open in workspace

recordType

paper

region

Global