arXiv cs.AI· Adamo Orsini, Seyed Mehdi Ayyoubzadeh, Sadman Rakib Pinon, Hannuo Zhang, Koosha Gholipour Baradari, Yuanhao Yu, Xinxin Zuo, Yang Wang·· 12 小时前AI 评分38
TAG-Nav：面向移动 GUI 导航的任务无关图探索框架
Not All Graphs Are Maps: A Task-Agnostic Exploration Framework for Mobile GUI Navigation
AI 导读
TAG-Nav 是一个任务无关的图导航框架，为现有 GUI 智能体加入可复用的目的地记忆，将离线探索蒸馏为应用功能、目标页面与路径点的紧凑记录。配套的 DestBench 仅评测导航、不涉及下游执行，图记忆使 UI-TARS-1.5-7B 严格导航成功率从 52.4% 提升至 58.3%，Qwen-VL-Max 从 59.5% 提升至 71.4%。
正文 · 原文
Abstract: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.
| Comments: | Accepted to Findings of AACL-IJCNLP 2026 |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.22672 [cs.AI] |
| (or arXiv:2610.22672v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22672 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Adamo Orsini [view email]
[v1]
Thu, 15 Oct 2026 21:40:34 UTC (5,535 KB)
来源：arXiv cs.AI · arxiv.org