English(EN) Learning to Route in Visual Space via Multi-Step Embedding Retrieval

新的VHOP-Router系统支持AI代理进行多步视觉搜索

作者 PulseAugur 编辑部 · [2 个来源] · 2026-09-30 01:28

研究人员开发了VHOP-Router，一个旨在通过实现多步嵌入检索来增强视觉代理搜索的新系统。这种方法绕过了代理在每一步都需要制定文本查询的需要，而是在视觉潜在空间内直接进行导航。实验表明检索性能显著提高，提高了代理搜索的成功率，并大幅减少了token使用量和API负载。 AI

影响增强了AI代理的视觉搜索能力，有可能提高复杂视觉任务的效率并降低计算成本。

排序理由该集群描述了一篇详细介绍AI代理搜索的新系统和基准的新研究论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 该集群描述了一篇详细介绍AI代理搜索的新系统和基准的新研究论文。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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: 8 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Tianyu Chen, Mingyuan Zhou, Jiaxing Wu · 2026-10-01 04:00

通过多步嵌入检索在视觉空间中学习路由

arXiv:2609.38743v1 Announce Type: new Abstract: LLM agents rely on retrieval tools to access external knowledge, yet visual agentic search remains severely bottlenecked by standard single-step retrievers. In current pipelines, the agent must issue text queries for every intermedi…
arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Jiaxing Wu · 2026-09-30 01:28

通过多步嵌入检索在视觉空间中学习路由

LLM agents rely on retrieval tools to access external knowledge, yet visual agentic search remains severely bottlenecked by standard single-step retrievers. In current pipelines, the agent must issue text queries for every intermediate step, struggling when visual clues are diffi…