用开源模型让网页智能代理更省钱高效
Surfer-H Meets Holo1: Cost-Efficient Web Agent Powered by Open Weights
- 结合视觉语言模型实现用户自定义网页任务
- 在WebVoyager上达92.2%准确率，成本效益最优
- 适合研究智能代理与低成本部署的开发者
我们提出Surfer-H，一种基于开源视觉语言模型（VLM）的低成本网页智能代理，可执行用户自定义网络任务。其核心是新发布的开放权重模型Holo1，专为网页导航与信息抽取优化，训练数据涵盖公开网页内容、合成样本及自主生成的智能体数据。Holo1在通用界面基准和新提出的Web UI定位基准WebClick中表现领先。搭载Holo1后，Surfer-H在WebVoyager上达到92.2%的当前最优性能，实现了准确率与成本效率的帕累托最优。为推动智能体系统研究，我们开源了WebClick评估数据集及Holo1模型权重。
原文摘要 · Abstract (English)
We present Surfer-H, a cost-efficient web agent that integrates Vision-Language Models (VLM) to perform user-defined tasks on the web. We pair it with Holo1, a new open-weight collection of VLMs specialized in web navigation and information extraction. Holo1 was trained on carefully curated data sources, including open-access web content, synthetic examples, and self-produced agentic data. Holo1 tops generalist User Interface (UI) benchmarks as well as our new web UI localization benchmark, WebClick. When powered by Holo1, Surfer-H achieves a 92.2% state-of-the-art performance on WebVoyager, striking a Pareto-optimal balance between accuracy and cost-efficiency. To accelerate research advancement in agentic systems, we are open-sourcing both our WebClick evaluation dataset and the Holo1 model weights.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。