Saved in:
Bibliographic Details
Main Authors: Zhou, Yuqi, Wang, Shuai, Dai, Sunhao, Jia, Qinglin, Du, Zhaocheng, Dong, Zhenhua, Xu, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.03743
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913720194564096
author Zhou, Yuqi
Wang, Shuai
Dai, Sunhao
Jia, Qinglin
Du, Zhaocheng
Dong, Zhenhua
Xu, Jun
author_facet Zhou, Yuqi
Wang, Shuai
Dai, Sunhao
Jia, Qinglin
Du, Zhaocheng
Dong, Zhenhua
Xu, Jun
contents The advancement of visual language models (VLMs) has enhanced mobile device operations, allowing simulated human-like actions to address user requirements. Current VLM-based mobile operating assistants can be structured into three levels: task, subtask, and action. The subtask level, linking high-level goals with low-level executable actions, is crucial for task completion but faces two challenges: ineffective subtasks that lower-level agent cannot execute and inefficient subtasks that fail to contribute to the completion of the higher-level task. These challenges stem from VLM's lack of experience in decomposing subtasks within GUI scenarios in multi-agent architecture. To address these, we propose a new mobile assistant architecture with constrained high-frequency o}ptimized planning (CHOP). Our approach overcomes the VLM's deficiency in GUI scenarios planning by using human-planned subtasks as the basis vector. We evaluate our architecture in both English and Chinese contexts across 20 Apps, demonstrating significant improvements in both effectiveness and efficiency. Our dataset and code is available at https://github.com/Yuqi-Zhou/CHOP
format Preprint
id arxiv_https___arxiv_org_abs_2503_03743
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CHOP: Mobile Operating Assistant with Constrained High-frequency Optimized Subtask Planning
Zhou, Yuqi
Wang, Shuai
Dai, Sunhao
Jia, Qinglin
Du, Zhaocheng
Dong, Zhenhua
Xu, Jun
Artificial Intelligence
The advancement of visual language models (VLMs) has enhanced mobile device operations, allowing simulated human-like actions to address user requirements. Current VLM-based mobile operating assistants can be structured into three levels: task, subtask, and action. The subtask level, linking high-level goals with low-level executable actions, is crucial for task completion but faces two challenges: ineffective subtasks that lower-level agent cannot execute and inefficient subtasks that fail to contribute to the completion of the higher-level task. These challenges stem from VLM's lack of experience in decomposing subtasks within GUI scenarios in multi-agent architecture. To address these, we propose a new mobile assistant architecture with constrained high-frequency o}ptimized planning (CHOP). Our approach overcomes the VLM's deficiency in GUI scenarios planning by using human-planned subtasks as the basis vector. We evaluate our architecture in both English and Chinese contexts across 20 Apps, demonstrating significant improvements in both effectiveness and efficiency. Our dataset and code is available at https://github.com/Yuqi-Zhou/CHOP
title CHOP: Mobile Operating Assistant with Constrained High-frequency Optimized Subtask Planning
topic Artificial Intelligence
url https://arxiv.org/abs/2503.03743