ChatPaper.aiChatPaper

AgentStore:可扩展集成异构代理作为专门化通用计算助手

AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant

October 24, 2024
作者: Chengyou Jia, Minnan Luo, Zhuohang Dang, Qiushi Sun, Fangzhi Xu, Junlin Hu, Tianbao Xie, Zhiyong Wu
cs.AI

摘要

由于其巨大潜力来增强人机交互,能够自动化复杂计算机任务的数字代理引起了广泛关注。然而,现有的代理方法在泛化和专业化能力方面存在不足,特别是在处理真实环境中的开放式计算机任务时。受App商店丰富功能的启发,我们提出AgentStore,这是一个可扩展的平台,旨在动态整合异构代理以自动化计算机任务。AgentStore赋予用户整合第三方代理的能力,使系统能够不断丰富其功能并适应快速演化的操作系统。此外,我们提出了一种新颖的核心元代理MetaAgent,采用AgentToken策略来高效管理各种代理,并利用它们的专业和通用能力来执行特定领域和系统范围的任务。在三个具有挑战性的基准测试上进行的大量实验表明,AgentStore超越了先前具有狭窄能力的系统的局限性,特别是在OSWorld基准测试中,从11.21%显著提高到23.85%,结果翻了一番多。全面的定量和定性结果进一步证明了AgentStore在泛化和专业化方面增强代理系统的能力,突显了其发展专业通用计算机助手的潜力。我们所有的代码将在https://chengyou-jia.github.io/AgentStore-Home 上公开。
English
Digital agents capable of automating complex computer tasks have attracted considerable attention due to their immense potential to enhance human-computer interaction. However, existing agent methods exhibit deficiencies in their generalization and specialization capabilities, especially in handling open-ended computer tasks in real-world environments. Inspired by the rich functionality of the App store, we present AgentStore, a scalable platform designed to dynamically integrate heterogeneous agents for automating computer tasks. AgentStore empowers users to integrate third-party agents, allowing the system to continuously enrich its capabilities and adapt to rapidly evolving operating systems. Additionally, we propose a novel core MetaAgent with the AgentToken strategy to efficiently manage diverse agents and utilize their specialized and generalist abilities for both domain-specific and system-wide tasks. Extensive experiments on three challenging benchmarks demonstrate that AgentStore surpasses the limitations of previous systems with narrow capabilities, particularly achieving a significant improvement from 11.21\% to 23.85\% on the OSWorld benchmark, more than doubling the previous results. Comprehensive quantitative and qualitative results further demonstrate AgentStore's ability to enhance agent systems in both generalization and specialization, underscoring its potential for developing the specialized generalist computer assistant. All our codes will be made publicly available in https://chengyou-jia.github.io/AgentStore-Home.

Summary

AI-Generated Summary

PDF332November 16, 2024