Towards Enterprise-Ready Computer Using Generalist Agent

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Marreed, Sami, Oved, Alon, Yaeli, Avi, Shlomov, Segev, Levy, Ido, Akrabi, Offer, Sela, Aviad, Adi, Asaf, Mashkif, Nir
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916833555120128
author Marreed, Sami
Oved, Alon
Yaeli, Avi
Shlomov, Segev
Levy, Ido
Akrabi, Offer
Sela, Aviad
Adi, Asaf
Mashkif, Nir
author_facet Marreed, Sami
Oved, Alon
Yaeli, Avi
Shlomov, Segev
Levy, Ido
Akrabi, Offer
Sela, Aviad
Adi, Asaf
Mashkif, Nir
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_01861
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Enterprise-Ready Computer Using Generalist Agent
Marreed, Sami
Oved, Alon
Yaeli, Avi
Shlomov, Segev
Levy, Ido
Akrabi, Offer
Sela, Aviad
Adi, Asaf
Mashkif, Nir
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Multiagent Systems
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.
title Towards Enterprise-Ready Computer Using Generalist Agent
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2503.01861