通过预判网页结构加速网页代理，成本降1.9倍，延迟减33.4%。
Skim: Speculative Execution for Fast and Efficient Web Agents
- 基于网站规律性预生成路径，跳过重计算步骤。
- 在不丢精度前提下，任务开销降低1.9倍，延迟减少33.4%。
- 适合需高频访问固定结构网页的自动化场景。
Skim 是一种针对网页代理的推测执行框架，利用专用网站的可预测结构。当前网页代理成本并非任务本身所致，而是由代理组成方式导致：无论任务复杂度如何，均对每一步执行前端模型推理、浏览器渲染和 ReAct 式规划。Skim 的核心观察是，同一类型查询在网站中具有稳定的 URL 模式、答案格式和任务到轨迹的映射关系，因此多数查询可完全跳过这些高负载组件。离线分析器为每个网站捕获这些模式一次。运行时，Skim 将查询匹配模板，合成目标 URL 并用小型模型提取答案。轻量级验证器对快速路径输出进行查询与模式校验；罕见误判将回退至完整代理，且以快速路径最终的 URL 作为热启动，保留上游轨迹进度。在标准网页代理基准上，搭配三种主干代理（WebVoyager、AgentOccam、BrowserUse），Skim 将任务中位成本降低 1.9 倍，延迟减少 33.4%，无准确率损失。
原文摘要 · Abstract (English)
Skim is a speculative execution framework for web agents that exploits the predictable structure of purpose-built websites. Today's web-agent expense is not intrinsic to the tasks but a property of how agents are composed: frontier-model inference, browser rendering, and ReAct-style planning are applied to every step of every task regardless of complexity. Skim's key observation is that websites enforce stable URL patterns, answer formats, and task-to-trajectory mappings across queries of the same type, so most queries can bypass these heavyweight components entirely. An offline profiler captures these patterns once per site. At runtime, Skim matches each query to a template, synthesizes the destination URL, and extracts the answer with a small model. A lightweight verifier gates each fast-path output against the query and schema; rare misspeculations cascade to the full agent, warm-started by the fast path's final URL to preserve upstream trajectory progress. Across standard web-agent benchmarks paired with three backboneagents (WebVoyager, AgentOccam, BrowserUse), Skim reduces median per-task cost by 1.9x and latency by 33.4% with no accuracy loss.
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。