EconSkills：研究实时经济数据上Web智能体的技能迁移与检索

中文摘要 AI 辅助

Web智能体经常访问相同的网站，但大多数评估却丢弃了早期成功交互中学到的程序。我们引入了EconSkills，一个技能库和评估框架，它将经过验证的EconWebArena轨迹提炼为参数化的标准操作程序，用于检索实时经济数据。每个技能记录其范围、导航程序、站点特定指南、验证检查和恢复步骤，同时用占位符替换源实例值。EconSkills区分了两个问题：一个已知的相关程序是否能迁移到保留的任务上，以及智能体在从库中选择时是否能保留这种优势。在受控迁移中，匹配的技能比无技能提示提高了成功率，并在配对成功中需要更少的步骤，而抽象化比重放原始轨迹更有效。在库规模上，检索总体上与无技能基线相当，并在直接覆盖的任务上表现最佳；按覆盖率分层的结果显示，未覆盖任务上的近似匹配抵消了这些收益。浏览器轨迹进一步识别了程序性指导何时缩短特定门户的导航，以及何时需要语义验证。这些结果确立了可复用的经济Web程序可以跨任务实例迁移，并为覆盖率感知的选择和上下文传递提供了具体的设计目标。

英文摘要

Web agents often revisit the same sites, yet most evaluations discard the procedures learned in earlier successful interactions. We introduce EconSkills, a skill library and evaluation framework that distills verified EconWebArena trajectories into parameterized standard operating procedures for retrieving live economic data. Each skill records its scope, navigation procedure, site-specific guidance, verification checks, and recovery steps while replacing source-instance values with placeholders. EconSkills separates two questions: whether a known relevant procedure transfers to a held-out task, and whether an agent can retain that benefit when selecting from a library. In controlled transfer, matched skills improve success over no-skill prompting and require fewer steps on paired successes. Under the evaluated prompt formats, the parameterized skill prompt substantially outperforms the corresponding raw-trajectory prompt. With the full 50-skill library, retrieval is competitive with the no-skill baseline overall and performs best on tasks with a direct family match; approximate matches on other tasks offset these gains. Browser trajectories further identify when procedural guidance shortens portal-specific navigation and when semantic verification remains necessary. These results establish that reusable economic web procedures can transfer across task instances and provide a concrete design target for match-aware selection and context delivery.

发表机构

• Georgia Institute of Technology（佐治亚理工学院）
• Capital One（第一资本）

机构由 AI 辅助整理，请以论文原文为准。