ChatPaper.aiChatPaper

AgentStore:將異質代理整合為專業的通用計算助手,實現可擴展性

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

由於其巨大潛力來增強人機互動,能夠自動執行複雜計算機任務的數位代理引起了相當大的關注。然而,現有的代理方法在其泛化和專業化能力方面存在不足,特別是在處理現實環境中的開放式計算機任務時。受到App商店豐富功能的啟發,我們提出AgentStore,這是一個可擴展的平台,旨在動態整合異構代理以自動執行計算機任務。AgentStore賦予用戶整合第三方代理的能力,使系統能夠不斷豐富其功能並適應快速變化的操作系統。此外,我們提出了一種新型核心MetaAgent,採用AgentToken策略來有效管理各種代理並利用它們的專業和泛化能力,用於特定領域和系統範圍的任務。對三個具有挑戰性的基準進行的大量實驗表明,AgentStore超越了先前僅具有狹窄能力的系統的限制,特別是在OSWorld基準上實現了從11.21%到23.85%的顯著改進,超過了先前的結果。全面的定量和定性結果進一步證明了AgentStore在泛化和專業化方面提升代理系統的能力,突顯了其發展專業泛化計算機助手的潛力。我們所有的代碼將在https://chengyou-jia.github.io/AgentStore-Home 上公開提供。
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