用轻量架构模拟人类网页操作认知，低成本实现高效通用网页代理。
WebChallenger: A Reliable and Efficient Generalist Web Agent
- 构建结构化页面表示PageMem，分层抽象网页内容
- 三机制协同提升任务准确率：56.3%（WebArena）至70.9%（WorkArena）
- 无需微调开源模型，适合低预算通用网页自动化场景
自主网页导航对大语言模型代理仍具挑战性，现有最强通用系统依赖昂贵专有推理模型。我们指出问题不在于模型能力不足，而在于代理架构未能复现人类的三大认知优势：对页面关键区域的选择性注意力、对网站结构的持久记忆、对常见交互模式的程序流利性。为此提出WebChallenger框架，基于可确定性构建的结构化页面表示PageMem——从DOM生成的语义分层结构，包含短摘要。在此基础上设计三项机制：分而治之的观察管道，仅对任务相关区域深入提取；轻量级探索与记忆系统，单次遍历建立可复用的页面与元素行为地图；复合动作工作流，将多步交互压缩为单一动作，自动处理部分状态变化。三机制均作用于PageMem，使系统无需站点适配即可跨网站泛化。使用未微调的开源模型，在WebArena达56.3%、VisualWebArena达48.7%、Online-Mind2Web达51.0%、WorkArena达70.9%，接近前沿专有系统性能，成本仅为几分之一。代码已开源。
原文摘要 · Abstract (English)
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
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。