LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Guangyi, Zhao, Pengxiang, Liang, Yaozhen, Liu, Liang, Guo, Yaxuan, Xiao, Han, Lin, Weifeng, Chai, Yuxiang, Han, Yue, Ren, Shuai, Wang, Hao, Liang, Xiaoyu, Wang, WenHao, Wu, Tianze, Lu, Zhengxi, Chen, Siheng, LiLinghao, Xiong, Guanjing, Liu, Yong, Li, Hongsheng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909907127631872
author Liu, Guangyi
Zhao, Pengxiang
Liang, Yaozhen
Liu, Liang
Guo, Yaxuan
Xiao, Han
Lin, Weifeng
Chai, Yuxiang
Han, Yue
Ren, Shuai
Wang, Hao
Liang, Xiaoyu
Wang, WenHao
Wu, Tianze
Lu, Zhengxi
Chen, Siheng
LiLinghao
Wang, Hao
Xiong, Guanjing
Liu, Yong
Li, Hongsheng
author_facet Liu, Guangyi
Zhao, Pengxiang
Liang, Yaozhen
Liu, Liang
Guo, Yaxuan
Xiao, Han
Lin, Weifeng
Chai, Yuxiang
Han, Yue
Ren, Shuai
Wang, Hao
Liang, Xiaoyu
Wang, WenHao
Wu, Tianze
Lu, Zhengxi
Chen, Siheng
LiLinghao
Wang, Hao
Xiong, Guanjing
Liu, Yong
Li, Hongsheng
contents With the rapid rise of large language models (LLMs), phone automation has undergone transformative changes. This paper systematically reviews LLM-driven phone GUI agents, highlighting their evolution from script-based automation to intelligent, adaptive systems. We first contextualize key challenges, (i) limited generality, (ii) high maintenance overhead, and (iii) weak intent comprehension, and show how LLMs address these issues through advanced language understanding, multimodal perception, and robust decision-making. We then propose a taxonomy covering fundamental agent frameworks (single-agent, multi-agent, plan-then-act), modeling approaches (prompt engineering, training-based), and essential datasets and benchmarks. Furthermore, we detail task-specific architectures, supervised fine-tuning, and reinforcement learning strategies that bridge user intent and GUI operations. Finally, we discuss open challenges such as dataset diversity, on-device deployment efficiency, user-centric adaptation, and security concerns, offering forward-looking insights into this rapidly evolving field. By providing a structured overview and identifying pressing research gaps, this paper serves as a definitive reference for researchers and practitioners seeking to harness LLMs in designing scalable, user-friendly phone GUI agents. The collection of papers reviewed in this survey will be hosted and regularly updated on the GitHub repository: https://github.com/PhoneLLM/Awesome-LLM-Powered-Phone-GUI-Agents
format Preprint
id arxiv_https___arxiv_org_abs_2504_19838
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects
Liu, Guangyi
Zhao, Pengxiang
Liang, Yaozhen
Liu, Liang
Guo, Yaxuan
Xiao, Han
Lin, Weifeng
Chai, Yuxiang
Han, Yue
Ren, Shuai
Wang, Hao
Liang, Xiaoyu
Wang, WenHao
Wu, Tianze
Lu, Zhengxi
Chen, Siheng
LiLinghao
Wang, Hao
Xiong, Guanjing
Liu, Yong
Li, Hongsheng
Human-Computer Interaction
With the rapid rise of large language models (LLMs), phone automation has undergone transformative changes. This paper systematically reviews LLM-driven phone GUI agents, highlighting their evolution from script-based automation to intelligent, adaptive systems. We first contextualize key challenges, (i) limited generality, (ii) high maintenance overhead, and (iii) weak intent comprehension, and show how LLMs address these issues through advanced language understanding, multimodal perception, and robust decision-making. We then propose a taxonomy covering fundamental agent frameworks (single-agent, multi-agent, plan-then-act), modeling approaches (prompt engineering, training-based), and essential datasets and benchmarks. Furthermore, we detail task-specific architectures, supervised fine-tuning, and reinforcement learning strategies that bridge user intent and GUI operations. Finally, we discuss open challenges such as dataset diversity, on-device deployment efficiency, user-centric adaptation, and security concerns, offering forward-looking insights into this rapidly evolving field. By providing a structured overview and identifying pressing research gaps, this paper serves as a definitive reference for researchers and practitioners seeking to harness LLMs in designing scalable, user-friendly phone GUI agents. The collection of papers reviewed in this survey will be hosted and regularly updated on the GitHub repository: https://github.com/PhoneLLM/Awesome-LLM-Powered-Phone-GUI-Agents
title LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects
topic Human-Computer Interaction
url https://arxiv.org/abs/2504.19838