Preprint
Aug 2026
InSight-doc: Agentic Visual Perception for Long-Document Understanding
This work proposes InSight-doc, an agentic visual perception framework that treats visual resolution as an adaptive reasoning-time resource that starts from low resolution and selectively zooms into high-resolution regions for finer evidence, without relying on any external retriever.
Kaican Li, Weiyan Xie, Lewei Yao et al.
· 0 citations