Unverified50% confidenceFactExact time
Page-Agent 选择直接解析 DOM 树的路线，以结构化数据替代视觉感知
1
Sources
50%
Confidence
Long-term
Relevance
7/6/2026
First Seen
Sources
Alibaba Open-Sources Page-Agent: A Web AI Agent for Controlling Interfaces with Natural Language
githubGitHub Trending7/5/2026
Related Claims
VerifiedBrowser automation Agents locate webpage elements and simulate human operations through DOM parsing, visual recognition, or Accessibility Tree.76% similarUnverifiedThe AI uses Chrome DevTools MCP to obtain the page DOM tree in order to understand the page structure, rather than relying on simple image recognition.73% similarUnverifiedPage state compression strategies for browser agents include selective DOM pruning, accessibility tree serialization, and screenshot + Vision Language Model (VLM) multimodal approaches.73% similarUnverified页面状态表征主要有两种实现路径：基于DOM解析和基于视觉的方式；DOM解析精确度高、token消耗少但对动态渲染页面适应性弱，视觉方式更接近人类操作但计算成本更高72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/115342API
curl https://kongchang.com/api/v1/knowledge/claims/115342MCP
get_claim(id=115342)