Mobile Agent-Based Network Management

Neueste Paper

• MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation

  Chenzhi Liu, Yue Zhang, Jiehong Lin, Jianan Wang, Bo Wang, Zhongrui Wang, Xiaojuan Qi · 5. Oktober 2026

  Long-horizon mobile manipulation presents significant challenges due to compounding execution errors and capacity interference between locomotion and arm control. While recent Vision-Language-Action models excel at short-horizon tasks, they lack the hierarchical reasoning required for multi-stage ob…

• When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency

  Yulong Ming, Jie Xu, Zihan Wu, Xiaohua Jia · 5. Oktober 2026

  Compiling GUI procedures that agents execute repeatedly into programs can reduce their token costs. However, measuring payback and deciding when to compile have two challenges. First, compilation costs are uncertain because attempts can require repair and still fail to produce a usable program. Seco…

• The Backdrop Exposes What the World Around an Agent Costs It

  Nusrat Jahan Lia, Shubhashis Roy Dipta · 1. Oktober 2026

  Agent benchmarks test agents in worlds that stay still. Deployed agents work in worlds that other people also change. Someone texts the agent to send the money elsewhere or an order confirmation asks it to reply with a door code. We present BACKDROP, which asks how much of an agent's capability in a…

• AgBench: Agentic AI Benchmarks for Personal AI Devices

  Yizhou Han, Di Wu, Dhananjay Saikumar, Blesson Varghese · 1. Oktober 2026

  Agentic AI systems increasingly rely on cloud-hosted large language models for planning, tool use, and iterative execution, raising concerns about API cost and data exposure. Advances in personal AI devices enable agents to execute locally, but limited resources on device may affect task success and…

• MCP Error Messages Written for Developers Hurt the Most Capable Agents Most

  Xiaonan Xu, Wenjing Wu · 30. September 2026

  Many Model Context Protocol (MCP) servers wrap web APIs built for human developers, and their error messages tell the reader to run a command, edit a configuration, open a web page or wait. Many agents that read them can only call the server's tools. In 150 widely used MCP servers, 949 of 3,001 erro…

• PhoneCLI: From App Interfaces to Callable Commands for Mobile Agents

  Yangqin Jiang, Lingrui Xu, Chao Huang · 29. September 2026

  Mobile GUI agents operate through a perception--action loop: at each step they screenshot the device, invoke a vision--language model (VLM), and emit an action. It is slow, costly, and brittle, yet most of what it does is navigation---and everyday navigation is static, ordered, and endlessly repeate…

• Same Tasks, Different Apps: Why Mobile GUI Agents Fail to Generalize?

  Tien Tran, Namho Koh, Daiki E. Matsunaga, Ayush Jain, Kee Eung Kim · 29. September 2026

  Mobile GUI agents deployed in real settings must work across different applications that support the same functionality. Most existing benchmarks test each task in only one app, so a high score can mean the agent understands the task, or only that it knows that particular app. We introduce AnyAppBen…

• On Device Agentic Operation Caches -- Classifier-Centric NL-to-Action Generation

  Moghis Fereidouni, Anthony Arnold, Sumit Gulwani, Mark Marron, A. B. Siddique · 29. September 2026

  Agentic AI is increasingly being embedded in software applications to provide natural language interfaces to features and functionality. In most cases these agents are powered by enterprise (100+ billion parameter) or frontier class large language models that require substantial computational resour…

• Agentic Network Traffic Monitoring

  Manuel Tsoukatos, Hayden Jananthan, Jeremy Kepner · 29. September 2026

  As the use of agentic artificial intelligence increases in nearly every industry, there exists a widening attack surface. It is necessary to monitor agents to ensure that agents are acting in a way that is aligned with the users intent. Auditing an agent's network traffic provides a clear record of …

• MemAgent: Learning to Manage Heterogeneous Memory Providers for LLM Agents

  Yongxian Wei, Yilin Zhao, Runxi Cheng, Xinrui Chen, Chun Yuan, Yaoru Wang, Jiahong Yan, Dian Li · 29. September 2026

  Current agents remain largely stateless across tasks, limiting their ability to continually improve from prior interactions and making memory essential for long-horizon agentic behavior. Existing memory methods seek to reuse past experience, but most rely on a single memory representation (e.g., tra…

• Memory as Middleware for Self-Improving AI Agents

  K. R. Jayaram, Vatche Isahagian, Vinod Muthusamy, Gegi Thomas, Punleuk Oum, Gaodan Fang, Ashwath Vaithinathan Aravindan · 29. September 2026

  AI agents are stateless across sessions by default and therefore operationally amnesic: each session begins with little durable knowledge of prior failures, repairs, preferences, or successful strategies. As a result, agents repeat the same mistakes and discard hard-won experience. The dominant fix …

• A Safety-Bounded SDC-to-MCP Gateway for Medical AI Agents

  Bennet Gerlach, Stefan Fischer · 28. September 2026

  The Model Context Protocol (MCP) provides a common interface through which AI applications discover and use external resources and tools. It allows language-model agents to ground their reasoning in current system state and interact with heterogeneous services. In medical environments, however, expo…

• From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native Deeplinks

  Yuchen Sun, Chenglin Cai, Gongjie Zhang, Tianyu Xia, Quyu Kong, Panrong Tong, Zhengwen Zeng, Long Chen, Steven Hoi, Chongyang Zhang, Yue Wang · 28. September 2026

  Mobile GUI agents complete tasks using GUI actions like taps and swipes. These actions are broadly applicable across applications, but reaching a navigation interface. A single deeplink call can replace a sequence of screen-by-screen GUI actions. We therefore introduce hybrid interaction, using deep…

• AgentKernel: The Trust-Native Agentic Operating System

  Zhenhua Zou, Sheng Guo, Qiuyang Zhan, Lepeng Zhao, Shuo Li, Zhuotao Liu · 25. September 2026

  Modern AI agents routinely cross trust boundaries: they ingest untrusted content, combine it with privileged instructions, persist intermediate beliefs in long-term memory, and invoke privileged tools. This creates an attack surface in which malicious payloads can enter through model inputs and caus…

• Data Agents: Agentic Data Systems

  Guoliang Li, Peiyao Zhou, Xuanhe Zhou, Ji Sun, Yuyu Luo, Ju Fan · 22. September 2026

  Traditional data systems face profound limitations in the AI era, relying on human-crafted pipelines, lacking semantic understanding of heterogeneous data, and operating through rigid, reactive processing. To address these challenges, we propose a new paradigm called the Data Agent, designed to mana…

• AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows

  Rudrendu Kumar Paul, Sourav Nandy · 22. September 2026

  Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller models handle equally well. Existing routing solutions optimize single-turn query assignment but ignore a property unique to agentic workflows: subtask comp…

• A Scalable Trust Discovery Architecture for the Internet of Agents

  Song Zhang, Jiankang Yao, Hongtao Li, Xiaojun Zhang, Xugang Shen, Xin Li, Yanbiao Li · 18. September 2026

  The Internet of Agents is expected to enable large numbers of autonomous agents to discover, verify, and collaborate with each other across heterogeneous platforms. However, current agent protocols mainly address tool invocation and inter-agent communication, leaving scalable agent registration, tru…

• AgentPProf: Semantic Profiler for Long Horizon AI Agents

  Yusheng Zheng, Chaokun Chang, Yu Mao, Tianyuan Wu, Yuxi Huang, Tao Ma, Wenan Mao, Shuyi Cheng, Andi Quinn, Wei Wang · 18. September 2026

  AI agents increasingly orchestrate long-running activities with users, tools, and system resources for days and weeks. To improve agent quality, safety, and cost efficiency, developers need to determine where failures happen, what triggers unsafe effects, and which tasks consume the most budget, the…

• Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum

  Carolina Fortuna, Vid Han\v{z}el, Tim Strnad, Bla\v{z} Bertalani\v{c} · 17. September 2026

  As telecommunication networks evolve toward autonomous 5G-Advanced and 6G operations, agentic artificial intelligence (AI) workflows, where large language models (LLMs) execute multi-step reasoning, invoke diagnostic tools, retrieve domain knowledge, and coordinate across agent teams, are increasing…

• SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling

  Jiahao Wang, Kaizhan Lin, Kaixi Zhang, Jinbo Han, Xingda Wei, Sijie Shen, Chenguang Fang, Wenyuan Yu, Rong Chen, Haibo Chen · 16. September 2026

  LLM scheduling is critical to serving, yet how well existing designs fit agentic serving--where agents, not humans, issue the requests--remains unclear. Agents shift the workload in two ways: they consume many more tokens than humans, so the cluster must provide high throughput (TPS) at low latency;…

• BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents

  Tong Ye, Kunyang Han, Guozhi Wang, Longqiang Luo, Zhifeng Ding, Yongxiang Zhang, Xiaolei Shen, Yuxuan Zhang, Zhuping Zhang, Tao Xu, Yue Pan, Yucheng Zhao, Yupei Hu, Yuanjiang Ouyang, Danfeng Shen, Runqi Lin, Hongda Cai, Zhaoxiong Wang, Mengjia Yan, Yingjie Zhong, Chen Zhou, Zeyu Zhang, Xuwen Zhu, Penggang Shi, Mingcheng Luo, Ziyang Wu, Min Jin, Mingfu Shen, Zairong Xu, Fan Zhang, Hao Wang, Liang Liu, Zhulin Xie, Lijun Yao, Xiao Liang, Liangmin Wen, Liqiang Feng, Feilong Wu, Min Hu, Min Chen, Guanjing Xiong, Xiaohu Ruan, Xiaoxin Chen · 14. September 2026

  Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent gaps. Sandbox training produces a distribution mismatch with production environments; expensive real-device failures remain underutilized; and fixed bench…

• Diamond Agent: Agentic Control of Federated HPC Resources as a Service

  Haotian Xie, Junlin Chen, Mingkai Zheng, Yifan Zhu, Minu Mathew, Max Burnette, Yadu Babuji, Volodymyr Kindratenko, Shivaram Venkataraman, Kyle Chard, Ian Foster, Zhao Zhang · 9. September 2026

  Efficiently aggregating and orchestrating computing power across heterogeneous clusters for HPC workflows faces four practical challenges: preserving workflow context across independently administered clusters, moving large datasets between sites, reasoning about site-specific environments and sched…

• APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI Agents

  Jintian Feng, Long Chen, Xiao Yu, Jiayi Dai, Chenglong Liu, Haoru Wang, Zizhen Xue, Yuxuan Shi, Ziyang Wang, Yichen Gong · 9. September 2026

  Mobile GUI agents can execute tasks from natural-language instructions, but their evaluation remains difficult to make both realistic and reproducible. Existing benchmarks typically trade off these goals: simplified apps lack real-world mobile complexity, whereas live commercial apps introduce uncon…

• Improving Proficiency and Efficiency of Android GUI Agents via Self-Generating Tool Actions

  Juyong Lee, Woogyeol Jin, Kimin Lee · 9. September 2026

  Android agents using a hybrid action space that combines GUI actions and tool actions (e.g., accessing application data via APIs) remain largely underexplored, mainly due to the excessive effort required to create tools. To address this gap, we introduce DroidTool, a framework for augmenting the age…

• CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents

  Haoting Shi, Wenhao Wang, Weicheng Fang, Yaozhong Liang, Tian Jin, Pengxiang Zhao, Guangyi Liu, Siheng Chen, Yanfeng Wang · 7. September 2026

  Computer-use agents have advanced on benchmarks like OSWorld and AndroidWorld, but still act mostly through the GUI, often producing inefficient trajectories. Real-world computer work is hybrid, combining visual-state inspection with precise, high-throughput command-line operations, so capable agent…