# InSight-doc：面向长文档理解的智能体视觉感知框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-11 08:00
- AIHOT 分数：57
- AIHOT 链接：https://aihot.virxact.com/items/cmspx48gs094xro4hzkayb9on
- 原文链接：https://arxiv.org/abs/2608.10628

## AI 摘要

InSight-doc 提出将视觉分辨率作为自适应推理时资源的智能体框架，从低分辨率出发选择性放大高分辨率区域，无需外部检索器。通过 17.9K SFT 示例与 19.2K 强化学习样本训练，InSight-doc-8B 在文档 VQA 基准上提升 4.3–16.4 个准确率点，长文档场景下幻觉降低超 40%，推理延迟减少 41%–68%。代码、数据集与模型均已开源。

## 正文

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 of 17.9K high-quality SFT examples with region-level zoom-in trajectories, accompanied by 19.2K hard RL examples. Through SFT+RL, InSight-doc-8B improves the baseline by 4.3--16.4 accuracy points over document VQA benchmarks. On long documents, it reduces hallucination by more than 40% and inference latency by 41%--68% while maintaining an accuracy lead. Our code, datasets, and model are released at https://github.com/m-Just/InSight-doc .