EvoCUA：通过可扩展合成经验学习演进计算机使用代理

摘要

原生计算机使用智能体（CUA）的发展标志着多模态AI领域的重大飞跃。然而，其潜力目前受限于静态数据扩展的约束。现有范式主要依赖对静态数据的被动模仿，难以捕捉长周期计算机任务中固有的复杂因果动态。本研究提出EvoCUA——一种原生计算机使用的智能体模型。与静态模仿不同，EvoCUA将数据生成与策略优化整合为自我维持的进化循环。为缓解数据稀缺问题，我们开发了可验证合成引擎，能自主生成多样化任务并配备可执行验证器。为实现大规模经验获取，我们设计了可扩展基础设施，可协调数万个异步沙箱推演。基于这些海量轨迹数据，我们提出迭代进化学习策略以高效内化经验。该机制通过识别能力边界动态调节策略更新：强化成功操作流程，同时通过错误分析与自我校正将失败轨迹转化为丰富的监督信号。在OSWorld基准测试中的实证评估表明，EvoCUA实现了56.7%的成功率，创造了开源模型的新标杆。值得注意的是，EvoCUA显著超越此前最佳开源模型OpenCUA-72B（45.0%），并优于UI-TARS-2（53.1%）等闭源权重模型。关键的是，我们的结果验证了该方法的普适性：基于经验学习的进化范式在不同规模的基础模型中均能带来持续性能提升，为推进原生智能体能力开辟了稳健且可扩展的路径。

English

The development of native computer-use agents (CUA) represents a significant leap in multimodal AI. However, their potential is currently bottlenecked by the constraints of static data scaling. Existing paradigms relying primarily on passive imitation of static datasets struggle to capture the intricate causal dynamics inherent in long-horizon computer tasks. In this work, we introduce EvoCUA, a native computer use agentic model. Unlike static imitation, EvoCUA integrates data generation and policy optimization into a self-sustaining evolutionary cycle. To mitigate data scarcity, we develop a verifiable synthesis engine that autonomously generates diverse tasks coupled with executable validators. To enable large-scale experience acquisition, we design a scalable infrastructure orchestrating tens of thousands of asynchronous sandbox rollouts. Building on these massive trajectories, we propose an iterative evolving learning strategy to efficiently internalize this experience. This mechanism dynamically regulates policy updates by identifying capability boundaries -- reinforcing successful routines while transforming failure trajectories into rich supervision through error analysis and self-correction. Empirical evaluations on the OSWorld benchmark demonstrate that EvoCUA achieves a success rate of 56.7%, establishing a new open-source state-of-the-art. Notably, EvoCUA significantly outperforms the previous best open-source model, OpenCUA-72B (45.0%), and surpasses leading closed-weights models such as UI-TARS-2 (53.1%). Crucially, our results underscore the generalizability of this approach: the evolving paradigm driven by learning from experience yields consistent performance gains across foundation models of varying scales, establishing a robust and scalable path for advancing native agent capabilities.

EvoCUA：通过可扩展合成经验学习演进计算机使用代理

EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience

摘要

Support