PulseAugur
实时 18:24:45
English(EN) Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns

新的LLM代理SkillMigrator通过布局匹配重用网络技能

研究人员开发了SkillMigrator,这是一种新颖的方法,用于大型语言模型(LLM)网络代理在不同网站之间重用技能。与依赖指令相似性或站点元数据的先前方法不同,SkillMigrator基于页面布局结构匹配可迁移交互模式(TIPs)。这使得代理能够通过识别相似的结构布局在新页面上巩固技能,从而在WebArena和Mind2Web等基准测试中将LLM操作计数减少8-10%。 AI

影响 通过基于布局模式匹配实现跨不同网站的技能迁移,提高了LLM网络代理的效率。

排序理由 该集群包含一篇详细介绍LLM网络代理新方法的学术论文。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的LLM代理SkillMigrator通过布局匹配重用网络技能

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Shiqi He, Yue Cui, Feijie Wu, Xinyu Ma, Jiaheng Lu, Yaliang Li, Bolin Ding, Mosharaf Chowdhury ·

    Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns

    arXiv:2606.17645v1 Announce Type: new Abstract: Large language model (LLM) web agents are usually deployed as tool callers: each turn, the model reads a fresh page observation and emits one structured tool action. When every action is a low-level primitive, horizons grow quickly …

  2. arXiv cs.CL TIER_1 English(EN) · Mosharaf Chowdhury ·

    Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns

    Large language model (LLM) web agents are usually deployed as tool callers: each turn, the model reads a fresh page observation and emits one structured tool action. When every action is a low-level primitive, horizons grow quickly and so do policy-facing LLM completions, dominat…