# Towards Enterprise-Ready Computer Using Generalist Agent

arXiv: https://arxiv.org/abs/2503.01861 · HTML: https://mlsanity.com/paper/2503.01861/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 14 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Builds on (most cited first, 3 of 3)

- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents](https://mlsanity.com/paper/2410.06703/) (2024)

## Built on by (most cited first, 30 of 31)

- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Agent Learning via Early Experience](https://mlsanity.com/paper/2510.08558/) (2025)
- [REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites](https://mlsanity.com/paper/2504.11543/) (2025)
- [Scaling Agent Learning via Experience Synthesis](https://mlsanity.com/paper/2511.03773/) (2025)
- [Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction](https://mlsanity.com/paper/2506.07976/) (2025)
- [WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks](https://mlsanity.com/paper/2506.01952/) (2025)
- [FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents](https://mlsanity.com/paper/2510.03204/) (2025)
- [General Agent Evaluation](https://mlsanity.com/paper/2602.22953/) (2026)
- [Entropy-Preserving Reinforcement Learning](https://mlsanity.com/paper/2603.11682/) (2026)
- [A Subgoal-driven Framework for Improving Long-Horizon LLM Agents](https://mlsanity.com/paper/2603.19685/) (2026)
- [OpAgent: Operator Agent for Web Navigation](https://mlsanity.com/paper/2602.13559/) (2026)
- [Information-Theoretic Privacy Control for Sequential Multi-Agent LLM Systems](https://mlsanity.com/paper/2603.05520/) (2026)
- [WebGraphEval: Multi-Turn Trajectory Evaluation for Web Agents using Graph Representation](https://mlsanity.com/paper/2510.19205/) (2025)
- [AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systems](https://mlsanity.com/paper/2603.29848/) (2026)
- [AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systems](https://mlsanity.com/paper/2512.04367/) (2025)
- [Not All Skills Help: Measuring and Repairing Agent Knowledge](https://mlsanity.com/paper/2606.15390/) (2026)
- [Generative Caching for Structurally Similar Prompts and Responses](https://mlsanity.com/paper/2511.17565/) (2025)
- [WebNavigator: Global Web Navigation via Interaction Graph Retrieval](https://mlsanity.com/paper/2603.20366/) (2026)
- [Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents](https://mlsanity.com/paper/2607.05775/) (2026)
- [Inference-Time Distillation: Cost-Efficient Agents Without Fine-Tuning or Manual Prompt Engineering](https://mlsanity.com/paper/2512.02543/) (2025)
- [TabAgent: A Framework for Replacing Agentic Generative Components with Tabular-Textual Classifiers](https://mlsanity.com/paper/2602.16429/) (2026)
- [Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents](https://mlsanity.com/paper/2605.22608/) (2026)
- [On Theoretically-Driven LLM Agents for Multi-Dimensional Discourse Analysis](https://mlsanity.com/paper/2602.13713/) (2026)
- [Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents](https://mlsanity.com/paper/2605.06957/) (2026)
- [Governance by Construction for Generalist Agents](https://mlsanity.com/paper/2605.20874/) (2026)
- [Does The Way You Plan Matter? An Empirical Study of Planning Representations for LLM Web Agents](https://mlsanity.com/paper/2605.29927/) (2026)
- [Prismata: Confining Cross-Site Prompt Injection in Web Agents](https://mlsanity.com/paper/2607.08147/) (2026)
- [Toward Autonomous UI Exploration: The UIExplorer Benchmark](https://mlsanity.com/paper/2506.17779/) (2025)
- [Web Agents Should Use Typed Actions Instead of Click-Based Browsing](https://mlsanity.com/paper/2602.17245/) (2026)
- [Demand-Driven Context: A Methodology for Building Enterprise Knowledge Bases Through Agent Failure](https://mlsanity.com/paper/2603.14057/) (2026)

## Abstract (arXiv)

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.