研究人员开发了 OpenSearch-VL，这是一种新颖的、完全开源的、用于训练高级多模态深度搜索代理的方案。该方法利用了一个精心策划的高质量训练数据管道、一个结合文本和图像搜索以及各种处理能力的多元化工具环境，以及一个专门用于处理工具失败的训练算法。由此产生的代理在多项基准测试中表现出显著的性能提升，可与专有模型相媲美，旨在使前沿搜索代理研究更加易于获取。 AI
影响 提供开源工具和数据集，以普及对高级多模态搜索代理的研究，可能加速其开发和采用。
排序理由 该集群包含详细介绍新研究和训练 AI 代理的开源方案的学术论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominated by industrial giants. The typical industry recipe involves a highly resource-intensive pipeline spanning pre-training, continua…
arXiv:2605.05185v1 Announce Type: new Abstract: Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step reasoning. Despite rapid progress, top-tier multimod…
Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step reasoning. Despite rapid progress, top-tier multimodal search agents remain difficult to reproduce, …
<h2> <strong>Introduction</strong> </h2> <p>Have you ever think why Google gives you 10 links but cannot just answer your question directly? This is exactly the problem that researchers are solving with LLM based Deep Search Agents. In this blog post I will share what I learned f…