Scholarlink

We present VisualTreeSearch, a fully-deployed system for visualizing and understanding web agent test-time scaling. While test-time search algorithms substantially improve web agent success rates, they remain confined to research contexts with limited practical deployment. Our system bridges this gap with three key contributions: (1) a production-ready solution with cloud-based architecture, (2) an efficient API-based state reset mechanism that reduces state reset time from 50 to 2 s, and (3) an interactive web UI that transparently demonstrates the agent’s decision-making process. VisualTreeSearch provides an intuitive framework for both researchers and users to understand tree search execution in web agents.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

VisualTreeSearch: Understanding Web Agent Test-Time Scaling

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Danqing Zhang,
  • Yaoyao Qian,
  • Shiying He,
  • Yuanli Wang,
  • Jingyi Ni,
  • Junyu Cao

摘要

We present VisualTreeSearch, a fully-deployed system for visualizing and understanding web agent test-time scaling. While test-time search algorithms substantially improve web agent success rates, they remain confined to research contexts with limited practical deployment. Our system bridges this gap with three key contributions: (1) a production-ready solution with cloud-based architecture, (2) an efficient API-based state reset mechanism that reduces state reset time from 50 to 2 s, and (3) an interactive web UI that transparently demonstrates the agent’s decision-making process. VisualTreeSearch provides an intuitive framework for both researchers and users to understand tree search execution in web agents.