让网页智能体学会可执行的步骤化技能，提升长流程任务成功率。
WebXSkill: Skill Learning for Autonomous Web Agents
- 用合成轨迹提取可复用动作序列，生成带参数的动作程序与自然语言指引
- 在三个数据集上平均提升12.7%成功率，长流程任务表现更稳定
- 支持全自动与逐步指导两种模式，适配不同能力的LLM代理
由大语言模型驱动的自主网页代理在长周期浏览器操作中仍显脆弱。核心瓶颈在于现有技能形式存在“落地差距”：文本型工作流技能提供自然语言指导但无法直接执行，而代码型技能虽可运行却缺乏步骤级引导以支持适应或恢复。我们提出WebXSkill框架，通过可执行技能弥合这一鸿沟——每个技能同时包含参数化动作程序与步骤级自然语言说明。该框架分三阶段运行：技能提取从合成代理轨迹中挖掘可复用动作子序列并抽象为参数化技能；技能组织将它们索引成基于URL的图结构，实现上下文感知检索；技能部署提供两种互补模式：接地模式实现全自动化执行，引导模式则作为步骤指令供代理按其原生规划逐步遵循。WebXSkill在WebArena、WebVoyager和Online-Mind2Web上均展现持续改进。进一步发现，更优的技能部署模式取决于模型的规划与执行能力。代码已开源：https://github.com/aiming-lab/WebXSkill。
原文摘要 · Abstract (English)
Autonomous web agents powered by large language models (LLMs) remain brittle on long-horizon browser workflows. A key bottleneck is a grounding gap in existing skill formulations: textual workflow skills provide natural language guidance but cannot be directly executed, while code-based skills execute without giving the agent step-level guidance for adaptation or recovery. We introduce WebXSkill, a framework that bridges this gap with executable skills, each pairing a parameterized action program with step-level natural-language guidance. WebXSkill operates in three stages: skill extraction mines reusable action subsequences from readily available synthetic agent trajectories and abstracts them into parameterized skills, skill organization indexes them into a URL-based graph for context-aware retrieval, and skill deployment exposes two complementary modes, grounded mode for fully automated execution and guided mode where skills serve as step-by-step instructions the agent follows with its native planning. WebXSkill demonstrates consistent improvements on WebArena, WebVoyager, and Online-Mind2Web. We further find that better skill deployment mode depends on a model's plan and execution capability. The code is available at https://github.com/aiming-lab/WebXSkill.
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。