{
  "id": 18754,
  "url": "https://arxiv.org/abs/2608.10628",
  "title": "InSight-doc: Agentic Visual Perception for Long-Document Understanding",
  "summary": "Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot. In this work, we propose InSight-doc, an agentic visual perception framework that treats visual resolution as an adaptive reasoning-time resource. InSight-doc starts from low resolution and selectively zooms into high-resolution regions for finer evidence, without relying on any external retriever. To train such an agent, we construct an active-perception corpus o",
  "authors": "Kaican Li, Weiyan Xie, Lewei Yao, Jiannan Wu, Lanqing Hong, Yongxiang Huang",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T20:00:00.000Z",
  "fetched_at": "2026-08-13T05:10:37.786Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/18754",
  "original_url": "https://arxiv.org/abs/2608.10628",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}