← Back to all news
arXiv AI By Adamo Orsini, Seyed Mehdi Ayyoubzadeh, Sadman Rakib Pinon, Hannuo Zhang, Koosha Gholipour Baradari, Yuanhao Yu, Xinxin Zuo, Yang Wang

Not All Graphs Are Maps: A Task-Agnostic Exploration Framework for Mobile GUI Navigation

Read the original on arXiv AI →

The paper introduces TAG-Nav, a task‑agnostic graph navigation framework that augments mobile GUI agents with reusable destination memory, enabling offline exploration to be distilled into compact records of app functions, target pages, and waypoint routes. It also presents DestBench, a navigation‑only evaluation protocol that isolates route finding from downstream task execution. Experiments show that graph‑derived memory improves navigation success rates for several large‑language‑model agents, demonstrating that destination coverage and route cleanliness are key factors in the value of graph memory.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

Hugging Face Trending Papers
Oct 8

DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents

DeltaReplay introduces a step-level memory reuse framework for mobile GUI agents that selectively reuses parts of stored execution trajectories without modifying them. By representing trajectories as paths in a transition graph and separating actions into task-independent operations and task-specific parameters, the system compares each recorded step with the new task and current screen to decide whether to follow, adapt, or ignore it. Experiments on AndroidWorld and SPA-Bench show that this selective reuse can boost task success rates by up to 10.3 and 25.0 percentage points over a baseline agent.

agents
More like this →
arXiv AI
Oct 9

DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents

DeltaReplay is a step‑level memory reuse framework for mobile GUI agents that decides how to use stored execution trajectories without modifying them. It stores trajectories as paths in a transition graph, separating each action into a task‑independent operation and task‑specific parameters, and compares each recorded step with the new task and current screen to decide whether to follow, adapt, or ignore it. Experiments on AndroidWorld and SPA‑Bench show that DeltaReplay can increase task success rates by up to 10.3 and 25.0 percentage points over a base agent with the same backbone.

By Yudong Bai, Yihong Chen, Quanming Yao, Yaqing Wang
agents
More like this →