mlsanityData to 14 Oct 2026

Towards Enterprise-Ready Computer Using Generalist Agent

arXiv 2503.01861 ↗First posted 24 Feb 2025cs.DC cs.AI cs.MAcited by 31

Not on the map. Why?

Cited by 24 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

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.

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

3 of 14 references.

References · 3

  1. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
  2. 2024AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agentscited by 401
  3. 2024ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agentscited by 133

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 12; 2026: 19.

31 papers.

Sort:

By area:

  1. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 398
  2. 2025Agent Learning via Early Experiencecited by 85
  3. 2025REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websitescited by 45
  4. 2025Scaling Agent Learning via Experience Synthesiscited by 44
  5. 2025Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interactioncited by 34
  6. 2025WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Taskscited by 30
  7. 2025FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agentscited by 16
  8. 2026General Agent Evaluationcited by 13
  9. 2026Entropy-Preserving Reinforcement Learningcited by 11
  10. 2026A Subgoal-driven Framework for Improving Long-Horizon LLM Agentscited by 11
  11. 2026OpAgent: Operator Agent for Web Navigationcited by 8
  12. 2026Information-Theoretic Privacy Control for Sequential Multi-Agent LLM Systemscited by 8
19 more
  1. 2025WebGraphEval: Multi-Turn Trajectory Evaluation for Web Agents using Graph Representationcited by 7
  2. 2026AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systemscited by 7
  3. 2025AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systemscited by 6
  4. 2026Not All Skills Help: Measuring and Repairing Agent Knowledgecited by 6
  5. 2025Generative Caching for Structurally Similar Prompts and Responsescited by 3
  6. 2026WebNavigator: Global Web Navigation via Interaction Graph Retrievalcited by 3
  7. 2026Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agentscited by 3
  8. 2025Inference-Time Distillation: Cost-Efficient Agents Without Fine-Tuning or Manual Prompt Engineeringcited by 2
  9. 2026TabAgent: A Framework for Replacing Agentic Generative Components with Tabular-Textual Classifierscited by 2
  10. 2026Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agentscited by 2
  11. 2026On Theoretically-Driven LLM Agents for Multi-Dimensional Discourse Analysiscited by 1
  12. 2026Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agentscited by 1
  13. 2026Governance by Construction for Generalist Agentscited by 1
  14. 2026Does The Way You Plan Matter? An Empirical Study of Planning Representations for LLM Web Agentscited by 1
  15. 2026Prismata: Confining Cross-Site Prompt Injection in Web Agentscited by 1
  16. 2025Toward Autonomous UI Exploration: The UIExplorer Benchmarkcited by 0
  17. 2026Web Agents Should Use Typed Actions Instead of Click-Based Browsingcited by 0
  18. 2026Demand-Driven Context: A Methodology for Building Enterprise Knowledge Bases Through Agent Failurecited by 0
  19. 2026A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Reference Architecture for Integrating Agentic AI into Enterprise Software: Responsibilities, Interactions, and Variability
  2. 2025AgentArch: A Comprehensive Benchmark to Evaluate Agent Architectures in Enterprise
  3. 2025Beyond Accuracy: A Multi-Dimensional Framework for Evaluating Enterprise Agentic AI Systems
  4. 2026Position: Agentic AI System Is a Foreseeable Pathway to AGI
  5. 2025Orchestrating Agents and Data for Enterprise: A Blueprint Architecture for Compound AI
  6. 2026EnterpriseBench Corecraft: Training Generalizable Agents on High-Fidelity RL Environments
  7. 2026Designing Intelligent Enterprise Agents: A Capability-Aligned Multi-Agent Architecture
  8. 2025Distinguishing Autonomous AI Agents from Collaborative Agentic Systems: A Comprehensive Framework for Understanding Modern Intelligent Architectures