Unverified50% confidenceFactExact time
Structure-aware chunking usually has two steps: first use a parser (such as a layout-aware parser for PDFs or a DOM parser for HTML) to extract a document tree with hierarchy, then decide merge or split strategies based on node type.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPage-Agent 选择直接解析 DOM 树的路线，以结构化数据替代视觉感知73% similarUnverifiedPage state compression strategies for browser agents include selective DOM pruning, accessibility tree serialization, and screenshot + Vision Language Model (VLM) multimodal approaches.70% similarUnverifiedScreen readers traverse the DOM tree node by node in a linear fashion, and users rely on heading-level navigation, form element labeling, and live region announcements to build a mental map of the interface.69% 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68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1031937API
curl https://kongchang.com/api/v1/knowledge/claims/1031937MCP
get_claim(id=1031937)