PulseAugur
中
实时 06:01:09
English(EN) BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents

新框架和基准推动移动 GUI 代理发展

研究人员正在开发新的框架和基准来提升移动 GUI 代理的能力。BlueLM-GUI,一个 35B-A3B 代理,专注于真实设备训练和错误纠正,以在 MobileGUI-VBench 等基准上取得更高性能。JarvisGUI 解决了跨设备工作流问题,突显了当前代理在状态转移和长时依赖方面的困难。DroidTool 引入了自生成工具来提高 Android 代理的效率和性能,而 APPSim-Bench 提供了可控的模拟应用程序以进行可复现的评估,揭示了自主移动执行仍然是一个重大挑战。AgentLens 探索了自适应视觉模态以改善移动 GUI 代理中的人机交互。 AI

影响 这些进展旨在提高移动 GUI 代理的可靠性、效率和用户交互性,有可能加速其在实际应用中的普及。

排序理由 多篇研究论文介绍了用于移动 GUI 代理的新框架、基准和方法论。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →

新框架和基准推动移动 GUI 代理发展

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
多篇研究论文介绍了用于移动 GUI 代理的新框架、基准和方法论。
Source corroboration
6 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
paper, product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
74 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [6]

  1. arXiv cs.AI TIER_1 English(EN) · 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, Yingj… ·

    BlueLM-GUI 技术报告:以真实设备为中心的自改进移动 GUI 智能体飞轮

    arXiv:2609.12394v2 Announce Type: replace Abstract: 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 environmen…

  2. arXiv cs.AI TIER_1 English(EN) · Zixiang Chen, Yuheng Lu, Zihao Cheng, Zeming Liu, Jizeng Bai, Ziye Huang, Zhiyin Lin, Zihan Li, Yuhang Guo, Yunhong Wang, Haifeng Wang ·

    JarvisGUI:迈向具有动态任务组合的跨设备GUI代理

    arXiv:2609.10451v1 Announce Type: new Abstract: Real-world GUI usage frequently involves workflows that span multiple devices and platforms, requiring the transfer of intermediate results, maintenance of shared state, and coordination across heterogeneous environments. However, e…

  3. arXiv cs.AI TIER_1 English(EN) · Juyong Lee, Woogyeol Jin, Kimin Lee ·

    通过自生成工具操作提高Android GUI代理的熟练度和效率

    arXiv:2609.06792v1 Announce Type: new Abstract: 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 …

  4. arXiv cs.AI TIER_1 English(EN) · Jintian Feng, Long Chen, Xiao Yu, Jiayi Dai, Chenglong Liu, Haoru Wang, Zizhen Xue, Yuxuan Shi, Ziyang Wang, Yichen Gong ·

    APPSim-Bench:连接真实应用与移动GUI代理的可复现评估

    arXiv:2609.07712v1 Announce Type: new Abstract: 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-w…

  5. arXiv cs.AI TIER_1 English(EN) · Jeonghyeon Kim, Byeongjun Joung, Junwon Lee, Joohyung Lee, Taehoon Min, Sunjae Lee ·

    AgentLens:移动GUI代理中用于人机交互的自适应视觉模态

    arXiv:2604.20279v3 Announce Type: replace-cross Abstract: Mobile GUI agents can automate smartphone tasks by interacting directly with app interfaces, but how they should communicate with users during execution remains underexplored. Existing systems rely on two extremes: foregro…

  6. Hugging Face Daily Papers TIER_1 English(EN) ·

    APPSim-Bench:连接真实应用与移动GUI代理的可复现评估

    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 …