arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.01861cs.DCcs.AIcs.MA

面向企业级应用的通用智能体计算机系统

Towards Enterprise-Ready Computer Using Generalist Agent

IBM Research(IBM研究院)

Sami Marreed, Alon Oved, Avi Yaeli, Segev Shlomov, Ido Levy, Offer Akrabi, Aviad Sela, Asaf Adi, Nir Mashkif

AI总结:

本文提出面向企业级应用的通用智能体计算机系统,通过结合先进智能体AI技术与迭代评估改进方法,在WebArena和AppWorld基准上达到新最先进性能,并总结了开发经验与未来挑战。

摘要:

本文介绍了我们正在进行的面向企业级应用的通用智能体计算机(CUGA)系统开发工作。我们的研究强调了构建适用于企业环境的智能体系统的演进性质。通过将最先进的智能体AI技术与迭代评估、分析和改进的系统性方法相结合,我们实现了快速且成本效益高的性能提升,特别是在WebArena和AppWorld基准测试上达到了新的最先进性能。我们详细介绍了开发路线图、促进从失败中快速学习和系统持续改进的方法与工具,并讨论了企业采用的关键经验教训和未来挑战。

英文摘要:

This paper presents our ongoing work toward developing an enterprise-ready Computer Using Generalist Agent (CUGA) system. Our research highlights the evolutionary nature of building agentic systems suitable for enterprise environments. By integrating state-of-the-art agentic AI techniques with a systematic approach to iterative evaluation, analysis, and refinement, we have achieved rapid and cost-effective performance gains, notably reaching a new state-of-the-art performance on the WebArena and AppWorld benchmarks. We detail our development roadmap, the methodology and tools that facilitated rapid learning from failures and continuous system refinement, and discuss key lessons learned and future challenges for enterprise adoption.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑