ai.hackcv
论文精选 61arXiv

Plover: Steering GUI Agents through Plan-Centric Interaction· Plover:基于计划的 GUI 代理交互

Graphical user interface (GUI) automation remains challenging in real-world environments, where dynamic layouts, unexpected dialogs, and evolving interface states can cause autonomous agents to drift from user intent. Recent vision-based multimodal agents improve flexibility by operating directly over screenshots and natural language instructions, but planning and adaptation often remain internal, limiting users' ability to inspect, supervise, or correct system behavior. We present Plover, a plan-centric vision-based GUI automation system that externalizes task plans and replanning as persistent, inspectable, and revisable artifacts. Through a planner--executor architecture, Plover supports explicit supervision of evolving execution, localized correction through editable plans, natural-lan

AI 解读论文

基于计划的 GUI 代理交互系统,提高自动化任务的监督与修正能力

核心方法
Plover 采用规划-执行架构,将任务计划和重规划过程外部化为持久、可检查和可修改的工件
适合谁读
研究者 / 工程师
要解决的问题
现有的 GUI 自动化系统在动态布局和意外对话框等不确定因素下难以保持与用户意图的一致性
关键实验
未提供
主要贡献
提供了一个用户可以监督、审查和纠正执行过程的 GUI 自动化系统,增强了系统的透明度和可控性
意义与局限
该系统解决了 GUI 自动化中的透明度和适应性问题,但在复杂环境下的鲁棒性仍需进一步验证
领域:cs.AI作者:Madhumitha Venkatesan、Shicheng Wen、Jiajing Guo
相关推荐

本站内容由 LLM 精选聚合,原文版权归 arXiv 所有 · 摘录仅供参考