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.

翻译：Skim是一种面向网络代理的推测执行框架，它利用结构化网站的可预测性。当前网络代理的高昂开销并非任务本身固有的属性，而是代理编排方式的产物：无论任务复杂度如何，前沿模型推理、浏览器渲染和ReAct式规划都应用于每个任务的每一步操作。Skim的核心发现是：同类型查询中，网站会强制执行稳定的URL模式、答案格式以及任务-轨迹映射关系，因此大多数查询可以完全绕过这些重量级组件。离线分析器为每个网站一次性捕获这些模式。在运行时，Skim将每个查询匹配到相应模板，合成目标URL，并通过小型模型提取答案。轻量级验证器根据查询和模式对每条快速路径输出进行门控检查；罕见的推测错误会回退到完整代理，并通过快速路径的最终URL进行热启动，以保留上游轨迹进度。在与三个骨干代理（WebVoyager、AgentOccam、BrowserUse）配对的标准网络代理基准测试中，Skim在不损失精度的前提下，将每个任务的中位成本降低了1.9倍，延迟降低了33.4%。