PulseAugur
中
实时 07:50:14
English(EN) Do Multi-Agents Dream of Electric Screens? Achieving 100% on AndroidWorld Through Task Decomposition

多智能体系统在Android UI控制基准测试中实现100%成功率

研究人员开发了Minitap's mobile-use,一个用于控制Android用户界面的多智能体系统。该系统在包含116个任务的AndroidWorld基准测试中达到了100%的通过率。Minitap系统使用五个不同的LLM智能体进行规划、子目标跟踪、状态捕获、决策和执行,以及确定性节点和读取设备输出及检测故障的机制。在MobileMiniWoB++基准测试上的进一步测试显示,比初始系统提高了7.1个百分点。 AI

影响 这项研究展示了一种用于复杂UI控制的多智能体系统的新颖方法,有望推动移动应用测试和交互的自动化。

排序理由 研究论文,详细介绍了用于Android UI控制的新多智能体系统及其基准性能。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

多智能体系统在Android UI控制基准测试中实现100%成功率

本文如何被排名

Signal score
27 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
研究论文,详细介绍了用于Android UI控制的新多智能体系统及其基准性能。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, product
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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Pierre-Louis Favreau, Jean-Pierre Lo, Clement Guiguet, Charles Simon-Meunier, Nicolas Dehandschoewercker, Allen G. Roush, Judah Goldfeder, Ravid Shwartz-Ziv ·

    多智能体是否会梦见电子屏幕?通过任务分解在AndroidWorld上实现100%

    arXiv:2602.07787v2 Announce Type: replace Abstract: We present Minitap's mobile-use, a multi-agent system for Android UI control, and evaluate it on the 116 tasks of AndroidWorld, on Android emulators in Minitap's cloud device infrastructure, real Pixel 7 phones from our device f…