English(EN) HyWe: Unifying Search and Operation for Real-World Hybrid Web Tasks

HyWe框架统一了AI代理的网络搜索和交互

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

研究人员推出HyWe，一个新颖的框架，旨在将复杂网络任务中的信息收集和页面交互能力统一到单个AI模型中。该框架利用专用的提示和工具集来执行子目标，并通过显式的切换机制和共享历史记录，使不同模式能够建立在彼此的发现之上。开发了一个新的基准HyWeBench，包含100个人类编写的任务，用于评估混合任务的完成情况，其中HyWe-35B取得了47.0%的成功率，显著优于现有的专用代理。 AI

影响这项研究可能带来更强大的AI代理，使其能够在网上执行复杂的多步任务，从而改善自动化和用户协助。

排序理由该集群描述了一篇介绍AI代理新框架和基准的新研究论文。[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 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇介绍AI代理新框架和基准的新研究论文。[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, 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]

arXiv cs.AI TIER_1 English(EN) · Zijian Cai, Haowei Liu, Kailai Chen, Lin Peng, Cong Wan, Ziqi Zhang, Chunfeng Yuan, Bing Li, Weiming Hu, Haiyang Xu · 2026-10-15 04:00

HyWe：统一真实世界混合网络任务的搜索与操作

arXiv:2610.16319v1 Announce Type: new Abstract: Real-world hybrid web tasks need both information gathering and page interaction, yet search-based and operation-based agents are developed and evaluated separately. To bridge this gap, we introduce HyWe, a framework that unifies bo…

本文如何被排名

报道来源 [1]

HyWe：统一真实世界混合网络任务的搜索与操作

相关实体

相关话题