让网页智能体只在关键信号触发时才读取页面，减少冗余信息干扰。
Signal-Driven Observation for Long-Horizon Web Agents
- 基于信号触发机制，仅在特定事件发生时才调用完整页面解析
- 将观察频率与动作频率解耦，避免上下文持续恶化
- 适合长周期网页任务，提升推理稳定性与效率
长期运行的网页智能体在每个动作步骤中都会摄入原始的DOM和可访问性树，通常包含数万令牌，导致上下文逐渐退化，任务未完成前推理能力已显著下降。我们指出，将观察频率与动作频率绑定是一种架构缺陷。借鉴递归语言模型中‘查询文档优于整体阅读’的洞察，提出信号驱动观察（SDO）：通过专用子调用读取完整DOM，仅返回任务相关元素及其选择器，并仅在轻量级信号检测器触发时重新调用——信号包括URL变化、新可见可交互元素、操作失败或外部浏览器事件。我们阐明了SDO引入的开放问题，并呼吁社区将观察压缩作为网页智能体设计的核心架构决策。
原文摘要 · Abstract (English)
Web agents operating over long horizons ingest raw DOM and accessibility trees -- routinely tens of thousands of tokens -- at every action step, causing progressive context degradation that erodes reasoning well before tasks complete. We argue that this coupling of observation frequency to action frequency is an architectural mistake. Drawing on the insight from Recursive Language Models that querying a document outperforms reading it wholesale, we propose Signal-Driven Observation (SDO): a dedicated sub-call reads the full DOM but returns only task-relevant elements and their selectors, and is re-invoked only when a lightweight signal detector fires -- triggered by URL transitions, newly visible interactive elements, action failures, or exogenous browser events. We outline the open problems SDO introduces and call on the community to treat observation compression as a core architectural decision in web agent design.
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。