SOURCE-LINKED INTELLIGENCE

DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Question Answering

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Real-world degradations such as blur, shadow, distortion, and moire patterns severely impair the document question-answering capabilities of Multimodal Large Language Models (MLLMs). Applying restoration tools before Visual Question Answering (VQA) is an intuitive solution. However, existing restoration approaches remain limited, as manually designing and executing restoration strategies is labor-intensive and requires domain expertise. Agentic restoration offers new possibilities for automation, yet existing frameworks primarily target natural images and pursue perceptual quality, overlooking

Read original source ↗ Open in workspace

recordType

paper

region

Global