With the advancement of multimodal large language models (MLLMs), building GUI agent systems has become an increasingly promising direction--especially for mobile platforms, given their rich app ecosystems and intuitive touch interactions. Yet mobile GUI agents face a critical dilemma: truly on-device models (4B or smaller) lack sufficient performance, while capable models (starting from 7B) are either too large for mobile deployment or prohibitively costly (e.g., cloud-only closed-source MLLMs). To resolve this, we propose OpenPhone, a mobile GUI agent system that leverages device-cloud collaboration to tap the cost-efficiency of on device models and the high capability of cloud models, while avoiding their drawbacks. Specifically, OpenPhone enhances Qwen2.5-VL-3B via two-stage SFT->GRPO training on synthetic GUI data for strong decision-making, integrates an efficient long-reasoning and memory management mechanism to utilize historical interactions under tight resources, and defaults to on-device execution--only escalating challenging subtasks to the cloud via real-time complexity assessment. Experiments on the online AndroidLab benchmark and diverse apps show OpenPhone matches or nears larger models, with a significant reduction in cloud costs.
Resource-Aware LLM Reasoning for Mobile Edge General Intelligence
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen(清华大学深圳国际研究生院,清华大学,深圳);College of Computing and Data Science, Nanyang Technological University, Singapore(南洋理工大学 computing 和数据科学学院,新加坡);Department of Electronic Engineering, Tsinghua University, Beijing(清华大学电子工程系,北京);State Key Laboratory of Space Network and Communications, Tsinghua University, Beijing(空间网络与通信国家重点实验室,清华大学,北京);Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing(北京信息科学与技术国家研究中心,清华大学,北京);Department of Electrical and Computer Engineering, Auburn University, Auburn, USA(阿伯丁大学电气与计算机工程系,阿伯丁,美国)
MANA: Towards Efficient Mobile Ad Detection via Multimodal Agentic UI Navigation
Department of Computer Science and Technology(计算机科学与技术系);University of Southern California(南加州大学);Shanghai Jiao Tong University(上海交通大学);State Key Laboratory of Internet Architecture(互联网架构国家重点实验室)
OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis
Shanghai AI Laboratory(上海人工智能实验室);School of Computing, National University of Singapore(新加坡国立大学计算机学院);Shanghai Jiaotong University(上海交通大学);Tsinghua University(清华大学)
An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing
Nanyang Technological University(南洋理工大学);Singapore Institute of Technology(新加坡理工学院);Seatrium New Energy Laboratory(Seatrium 新能源实验室);Ministry of Education (MOE) Tier 1(教育部 Tier 1);Research Innovation and Enterprise (RIE) 2025 Industry Alignment Fund-Industry Collaboration Projects (IAF-ICP)(研究创新与企业 (RIE) 2025 行业对齐基金-行业合作项目 (IAF-ICP))
BRAIN: Bayesian Reasoning via Active Inference for Agentic and Embodied Intelligence in Mobile Networks
School of Electrical Engineering and Computer Science, TU Berlin(技术大学柏林电气工程与计算机科学学院);Optical Zeitgeist Laboratory, INRS(光感知实验室,INRS);Federal Ministry of Research, Technology and Space (BMFTR, Germany)(德国联邦研究、科技与航天部)
Shanghai Jiao Tong University(上海交通大学);The Hong Kong University of Science and Technology(香港科技大学);University of Liverpool(利物浦大学);University of California Berkeley(加州大学伯克利分校);Shanghai Innovation Institute(上海创新研究院);University of California Davis(加州大学戴维斯分校);Virginia Tech(弗吉尼亚理工大学);University College London(伦敦大学学院)
Agentic TinyML for Intent-aware Handover in 6G Wireless Networks
Center for Ubiquitous Computing(无处不在计算中心);University of Oulu(奥卢大学);Department of Communication Systems(通信系统系);EURECOM;Department of Computer Science(计算机科学系);University of Helsinki(赫尔辛基大学);RISE Research Institutes of Sweden(瑞典研究机构);Department of Computer Science, Electrical and Space Engineering(计算机科学、电气与空间工程系);Luleå University of Technology(卢勒奥技术大学)
WirelessAgent++: Automated Agentic Workflow Design and Benchmarking for Wireless Networks
College of Electronics and Information Engineering, Shenzhen University(深圳大学电子与信息工程学院);Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology(香港理工大学电子与计算机工程系)
ARIA - An Agentic Framework for Autonomous Testing of Infotainment Systems
Critical Techworks, Portugal(Critical Techworks);Faculty of Engineering, University of Porto, Portugal(波尔图大学工程学院);LIACC, Faculty of Engineering, University of Porto, Portugal(波尔图大学工程学院LIACC);INESC TEC, Faculty of Engineering, University of Porto, Portugal(波尔图大学工程学院INESC TEC)
Lightweight Quantum Agent for Edge Systems: Joint PQC and NOMA Resource Allocation
School of Computer, Electronics and Information, Guangxi University(广西大学计算机电子与信息学院);Guangxi Key Laboratory of Multimedia Communications and Network Technology(广西多媒体通信与网络技术重点实验室);School of Computer Science and Engineering, Central South University(中南大学计算机科学与工程学院);College of Cyber Security, Jinan University(暨南大学网络安全学院);School of Computer Science and Engineering, South China University of Technology(华南理工大学计算机科学与工程学院);Pazhou Laboratory(琶洲实验室);Faculty of Computers and Artificial Intelligence, Hurghada University(Hurghada大学计算机与人工智能学院);Department of Information Systems, University of Maryland, Baltimore County (UMBC)(美国马里兰大学巴尔的摩县分校信息系统系)
Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
Beijing Institute of Technology(北京理工大学);State Key Laboratory of General Artificial Intelligence, BIGAI(通用人工智能国家重点实验室,BIGAI);DataCanvas;Beijing University of Posts and Telecommunications(北京邮电大学);Shenzhen MSU-BIT University(深圳MSU-BIT大学)