[论文] Not All Graphs Are Maps: A Task-Agnostic Exploration Framework for ...

论文概要

研究领域: NLP 作者: Adamo Orsini, Seyed Mehdi Ayyoubzadeh, Sadman Rakib Pinon, Hannuo Zhang, Koosha Gholipour Baradari, Yuanhao Yu, Xinxin Zuo, Yang Wang 发布时间: 2026-10-19 arXiv: 2610.22672

中文摘要

现代移动 GUI 智能体能感知可见屏幕、执行局部动作，但仍缺乏持久的应用级导航知识：功能在哪里、哪些页面含有它们、重复访问中哪些屏幕等价。本文提出 TAG-Nav：任务无关的图导航框架，为现有 GUI 智能体骨干包裹可复用的「目的地记忆」。在任何被评估指令出现之前，离线探索被蒸馏成应用功能、目标页面与路径点路线的紧凑记录；未来任务的目的地被覆盖时，TAG-Nav 检索目的地并提供路径指引，无需任务特定示范。这把「到达目的地」与「完成整个任务」解耦——许多任务共享「先到对的页面」这一前缀，而最终动作可能是输入内容、发送数据、购买、删除信息或修改敏感设置。为排除下游执行干扰、单独评估寻路，作者推出 DestBench：仅看智能体是否到达正确的「动作前目的地」屏幕的导航专用协议。受控图记忆研究显示：图记忆把 UI-TARS-1.5-7B 的严格导航成功率从 52.4%（无记忆）提升到 58.3%（自动 BFS 记忆），Qwen-VL-Max 从 59.5% 提升到 71.4%（同条件）。目的地覆盖率与路径干净度强烈影响图记忆的价值——图质量成为被测量的变量，而非探索的默认收益。

原文摘要

Modern mobile GUI agents can perceive visible screens and execute local actions, but they still lack persistent app-specific navigation knowledge: where functions live, which pages contain them, and which screens are equivalent across repeated visits. We introduce TAG-Nav, a Task-Agnostic Graph Navigation framework that wraps existing GUI-agent backbones with reusable destination memory. Offline exploration is distilled into compact records of app functions, target pages, and waypoint routes before any evaluated instruction is seen. When a future task's destination is covered, TAG-Nav retrieves the destination and provides route guidance without task-specific demonstrations. This separates mobile GUI destination navigation from full task completion: many tasks share the prefix of reaching the right page, while final actions may enter content, send data, make purchases, delete information, or change sensitive settings. To evaluate route finding without downstream execution confounds, we introduce DestBench, a navigation-only protocol that asks whether an agent reaches the correct pre-action destination screen. DestBench enables a controlled graph-memory study comparing no-memory agents with random, automated BFS, and clean graph memory. Graph-derived memory improves strict navigation success rate of UI-TARS-1.5-7B from 52.4% without graph memory to 58.3% with automated BFS memory, and improves Qwen-VL-Max success rate from 59.5% to 71.4% on the same conditions. Together, TAG-Nav and DestBench show that destination coverage and route cleanliness strongly shape graph-memory value, making graph quality a measured variable rather than an assumed benefit of exploration.

---

*自动采集于 2026-10-19*

#论文 #arXiv #NLP #小凯