CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements

Hugging Face Daily Papers Papers
computer-use-agents gui-automation recursive-improvement data-synthesis reinforcement-learning open-world

Summary

CUA-Master 提出嵌套双环递归改进框架，通过开放世界语料、自催化任务合成与反馈引导的快照回滚重试机制持续提升计算机使用代理（CUA）性能，其 27B 模型在 OSWorld Verified 等基准上取得竞争力表现。

Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data. Moreover, conventional optimization pipelines lack iterative feedback, while existing recursive improvement approaches often rely on self-generated experiences, limiting ability expansion and yielding diminishing returns. To address these challenges, we introduce CUA-Master, a nested double-loop recursive improvement framework. At the system level, an outer world-data-model flywheel continuously incorporates open-world corpus and leverages evolving model weaknesses to guide subsequent data construction and optimization iterations. At the data level, an inner flywheel couples open-world seeding and autocatalytic propagation. The former mines authentic workflows as seed tasks from instructional videos, and employs visual-semantic dual-path trajectory reconstruction; The latter transforms these seeds into reusable primitives for controllable synthesis of diverse, complex, and verifiable tasks. To enable efficient and reliable trajectory collection, we further introduce a feedback-guided snapshot-rollback retry mechanism in various real environments. Extensive experiments demonstrate that CUA-Master-27B achieves competitive performance across GUI-only and GUI-CLI hybrid benchmarks, scoring 80.2 on OSWorld Verified, 36.9 on OSWorld 2.0, 43.9 on WeaveBench, and 25.0 on Agents' Last Exam. Our framework also substantially improves the quality and efficiency of data synthesis, and exhibits continuous gains across recursive iterations.
Original Article
View Cached Full Text

Cached at: 11/03/26, 07:34 AM

Paper page - CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements

Source: https://huggingface.co/papers/2611.03126 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

CUA-Master uses nested recursive loops with open-world data and feedback-driven retries to continuously improve computer-use agents across diverse benchmarks.

Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data. Moreover, conventional optimization pipelines lack iterative feedback, while existing recursive improvement approaches often rely on self-generated experiences, limiting ability expansion and yielding diminishing returns. To address these challenges, we introduceCUA-Master, anested double-loop recursive improvementframework. At the system level, an outerworld-data-model flywheelcontinuously incorporatesopen-world corpusand leverages evolving model weaknesses to guide subsequent data construction and optimization iterations. At the data level, an inner flywheel couples open-world seeding andautocatalytic propagation. The former mines authentic workflows as seed tasks from instructional videos, and employsvisual-semantic dual-path trajectory reconstruction; The latter transforms these seeds intoreusable primitivesfor controllable synthesis of diverse, complex, and verifiable tasks. To enable efficient and reliable trajectory collection, we further introduce afeedback-guided snapshot-rollback retrymechanism in various real environments. Extensive experiments demonstrate thatCUA-Master-27B achieves competitive performance across GUI-only andGUI-CLI hybrid benchmarks, scoring 80.2 on OSWorld Verified, 36.9 on OSWorld 2.0, 43.9 on WeaveBench, and 25.0 on Agents’ Last Exam. Our framework also substantially improves the quality and efficiency of data synthesis, and exhibits continuous gains across recursive iterations.

View arXiv pageView PDFProject pageGitHub44Add to collection

Get this paper in your agent:

hf papers read 2611\.03126

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### yxl66666/CUAMaster-27B 27B• Updated19 minutes ago • 16 • 5

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2611.03126 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2611.03126 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale

Hugging Face Daily Papers

NorthCUA technical report presents an integrated system that scales computer-use agents via an Experience Flywheel, recursive self-improvement, staged learning, and reinforcement learning, achieving state-of-the-art open-source results on GUI grounding, desktop execution, and web interaction with its Nano, Mini, and Pro model family.

PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas

Hugging Face Daily Papers

论文提出 PersonaCUABench，通过 74 个任务和 44 个不同用户画像来评估计算机使用代理（CUA），发现相比原始指令，任务完成率平均下降 36%，表明 CUA 在满足真实用户的个性化需求和约束方面仍存在显著不足。

PRO-CUA: Process-Reward Optimization for Computer Use Agents

arXiv cs.AI

This paper introduces PRO-CUA, a process-reward optimization framework for training Computer Use Agents (CUAs) using iterative step-level reinforcement learning. The method decouples on-policy environment interaction from policy optimization, enabling dense credit assignment without relying on expert trajectories, and demonstrates effectiveness on live web benchmarks.