arXiv cs.AI· Yinzhu Quan, Zefang Liu·· 9 天前AI 评分27
EconSkills：面向 Web Agent 的技能迁移与检索研究，基于实时经济数据
EconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data
AI 导读
EconSkills 是一个技能库与评测框架，将 EconWebArena 中已验证的轨迹蒸馏为参数化标准操作流程，用于检索实时经济数据。在受控迁移测试中，匹配技能相比无技能提示提升了成功率，并在配对成功任务上所需步骤更少；参数化技能提示明显优于原始轨迹提示。使用完整 50 技能库时，检索整体与无技能基线相当，在存在直接同族匹配的任务上表现最佳。
正文 · 原文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2609.19523 [cs.AI] |
| (or arXiv:2609.19523v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.19523 arXiv-issued DOI via DataCite |
Submission history
From: Zefang Liu [view email]
[v1]
Thu, 17 Sep 2026 00:29:46 UTC (8,638 KB)
[v2]
Thu, 8 Oct 2026 04:53:11 UTC (8,638 KB)
来源：arXiv cs.AI · arxiv.org