English(EN) GUI-KV: Efficient GUI Agents via KV Cache with Spatio-Temporal Awareness

新的GUI-KV方法提高了视觉语言代理的效率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-09 04:00

研究人员开发了GUI-KV，一种提高利用视觉语言模型图形用户界面（GUI）代理效率的新颖方法。这些代理由于处理大量高分辨率屏幕截图而常常面临推理速度慢的问题。GUI-KV通过压缩键值缓存（存储过去信息的组件）来解决这个问题，而无需重新训练模型。该方法结合了空间显著性引导以保留重要的视觉细节，以及时间冗余评分以修剪重复的历史数据。实验表明，GUI-KV可以在保持准确性或甚至提高准确性的同时，显著降低计算成本，并且优于现有的缓存压缩技术。 AI

影响该方法可以实现更高效、更具成本效益的GUI代理部署以实现任务自动化。

排序理由这是一篇详细介绍用于提高AI代理效率的新技术方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍用于提高AI代理效率的新技术方法的论文。[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.CL TIER_1 English(EN) · Kung-Hsiang Huang, Haoyi Qiu, Yutong Dai, Caiming Xiong, Chien-Sheng Wu · 2026-10-09 04:00

GUI-KV：通过具有时空感知的KV缓存实现高效GUI代理

arXiv:2510.00536v2 Announce Type: replace Abstract: Graphical user interface (GUI) agents built on vision-language models have emerged as a promising approach to automate human-computer workflows. However, they also face the inefficiency challenge as they process long sequences o…

本文如何被排名

报道来源 [1]

GUI-KV：通过具有时空感知的KV缓存实现高效GUI代理

相关实体

相关话题