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.
@article{arxiv.2503.01861,
title = {Towards Enterprise-Ready Computer Using Generalist Agent},
author = {Sami Marreed and Alon Oved and Avi Yaeli and Segev Shlomov and Ido Levy and Offer Akrabi and Aviad Sela and Asaf Adi and Nir Mashkif},
journal= {arXiv preprint arXiv:2503.01861},
year = {2025}
}