构建企业级通用智能体系统，显著提升自动化任务表现
Towards Enterprise-Ready Computer Using Generalist Agent
- 融合前沿智能体技术与迭代评估优化流程
- 在WebArena和AppWorld基准上达新SOTA性能
- 适合关注AI自动化落地的企业研发团队
本文介绍了我们正在推进的企业级通用智能体系统（CUGA）的研究工作。研究强调了构建适用于企业环境的智能体系统的演化特性。通过将最先进的智能体AI技术与系统的迭代评估、分析和优化方法相结合，我们实现了快速且低成本的性能提升，尤其在WebArena和AppWorld基准测试中达到了新的最先进水平。文中详细阐述了开发路线图、促进快速学习失败经验并持续优化系统的工具与方法，并讨论了企业采用过程中的关键经验教训与未来挑战。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。