# WebChallenger：不依赖模型规模、通过架构设计提升自主网页导航的智能体框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-09 08:00
- AIHOT 分数：45
- AIHOT 链接：https://aihot.virxact.com/items/cmqb8gq9n00imslruorlnnhle
- 原文链接：https://arxiv.org/abs/2606.10423

## AI 摘要

WebChallenger 围绕核心模块 PageMem（从 DOM 确定性构建的带摘要语义层次页面结构）设计三种机制：分而治之的观测管线（让智能体扫读摘要、仅提取任务相关区域细节）、轻量级网站探索与记忆系统（遍历一次网站即可复用页面与元素行为地图）、以及将多步交互压缩为单步智能体动作的工作流。使用未经微调的开源模型，在 WebArena 上达 56.3%、VisualWebArena 48.7%、Online-Mind2Web 51.0%、WorkArena 70.9%，接近前沿闭源系统但成本极低。代码已开源。

## 正文

Autonomous web navigation remains challenging for LLM agents, and the strongest generalist systems rely on proprietary reasoning models whose inference cost is prohibitive for the repetitive tasks where such agents would be most useful. We argue this gap stems not from insufficient model capability but from agent architectures that fail to replicate three human cognitive advantages: selective attention to relevant page regions, persistent memory of website structure, and procedural fluency with common interaction patterns. We introduce WebChallenger, a web agent framework that addresses each gap through architecture design rather than model scale, built around PageMem: a structured page representation deterministically constructed from the DOM that exposes each page as a hierarchy of semantic sections with short summaries. On this shared substrate we build three mechanisms that mirror the three cognitive advantages: a divide-and-conquer observation pipeline that lets the agent skim section summaries and extract details only from task-relevant regions; a lightweight exploration and memory system that traverses each website once to build a reusable map of pages and element behaviors; and compound action workflows that collapse common multi-step interactions into single agent actions, handling partial state changes automatically. Because all three operate over PageMem, the framework generalizes across websites without site-specific adapters. Using off-the-shelf open-weight models without fine-tuning, our system achieves 56.3% on WebArena, 48.7% on VisualWebArena, 51.0% on Online-Mind2Web, and 70.9% on WorkArena, approaching frontier proprietary systems at a fraction of the cost. Our code is released at https://github.com/jayoohwang1/webchallenger