通过应用行为建模实现Web智能体的Token高效任务执行

中文摘要 AI 辅助

AI智能体在多种令人印象深刻的任务上的强劲表现正推动对智能体基础设施的前所未有的投资，然而处理token的成本正在迅速增加。Web智能体通过分析Web应用的用户界面（UI）并与之交互，来自动执行以自然语言描述的Web应用任务。本文介绍了OdoBot，一种新颖的Web智能体架构，与传统Web智能体相比，它能以极低的成本完成任务。这是通过利用基于分析成功任务执行演示而构建的底层应用行为模型来实现的。我们在Canvas学习管理系统（LMS）上对45个任务进行的实验表明，OdoBot使用的token比两个最先进的竞争智能体（Agent-E和WebVoyager）分别少44%和80%，同时在任务成功率上也超过了WebVoyager。

英文摘要

The strong performance of AI Agents across an impressive variety of tasks is driving an unprecedented investment in agentic infrastructures, however the cost of processing tokens is fast increasing. Web agents automate the execution of web-application tasks described in natural language, by analyzing the web-application's user interface (UI) and interacting with it. This work introduces OdoBot, a novel web-agent architecture that completes tasks at a fraction of the cost when compared to conventional web agents. This is achieved by leveraging a behavioral model of the underlying application constructed by analyzing successful task-execution demonstrations. Our experiments with 45 tasks on the Canvas Learning Management System (LMS) demonstrate that OdoBot uses 44% and 80% fewer tokens than two state-of-the-art competitor agents (Agent-E and WebVoyager), while also surpassing WebVoyager in terms of task success rate.

发表机构

• University of Alberta（阿尔伯塔大学）

机构由 AI 辅助整理，请以论文原文为准。