English(EN) STP-GUI: Spatially-Aware Token Pruning for Efficient Web-GUI Agents

新的 STP-GUI 方法提高了 Web-GUI 代理的效率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员开发了 STP-GUI，一个用于高效 Web-GUI 代理的新型框架，解决了高分辨率屏幕截图中视觉令牌过多的问题。与之前独立修剪令牌的方法不同，STP-GUI 采用了一种由查询驱动的、空间连贯的窗口级选择方法。该方法在保持局部视觉结构（对识别 GUI 元素至关重要）的同时，保留了细粒度的指令条件评分。实验表明，STP-GUI 在效率-性能之间取得了有利的权衡，在性能下降最小的情况下显著降低了推理延迟和 FLOPs，并有望迁移到移动 GUI 环境中。 AI

影响这项研究可能带来更高效、响应更快的 AI 代理，用于与 Web 和移动界面进行交互。

排序理由详细介绍 AI 代理新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

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

本文如何被排名

Signal score: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍 AI 代理新方法的学术论文。[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, 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: 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]

arXiv cs.CV TIER_1 English(EN) · Shuo Wang, Sifan Zhou, Xiaobo Wang, Tianyu Fu, Chenxu Zhao, Anyang Su, Hanning Wang, Ping Jiang, Minghui Wu · 2026-10-15 04:00

STP-GUI：用于高效 Web-GUI 代理的空间感知令牌修剪

arXiv:2610.20390v1 Announce Type: new Abstract: With the rapid development of vision-language models (VLMs), Web-GUI agents have achieved promising performance in interacting with real-world interfaces through screenshot-based grounding. However, high-resolution screenshots and m…

本文如何被排名

报道来源 [1]

STP-GUI：用于高效 Web-GUI 代理的空间感知令牌修剪

相关实体

相关话题