EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914274678407168 |
|---|---|
| author | Xue, Taofeng Peng, Chong Huang, Mianqiu Guo, Linsen Han, Tiancheng Wang, Haozhe Wang, Jianing Zhang, Xiaocheng Yang, Xin Zhao, Dengchang Ding, Jinrui Ma, Xiandi Xie, Yuchen Pei, Peng Cai, Xunliang Qiu, Xipeng |
| author_facet | Xue, Taofeng Peng, Chong Huang, Mianqiu Guo, Linsen Han, Tiancheng Wang, Haozhe Wang, Jianing Zhang, Xiaocheng Yang, Xin Zhao, Dengchang Ding, Jinrui Ma, Xiandi Xie, Yuchen Pei, Peng Cai, Xunliang Qiu, Xipeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_15876 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Xue, Taofeng Peng, Chong Huang, Mianqiu Guo, Linsen Han, Tiancheng Wang, Haozhe Wang, Jianing Zhang, Xiaocheng Yang, Xin Zhao, Dengchang Ding, Jinrui Ma, Xiandi Xie, Yuchen Pei, Peng Cai, Xunliang Qiu, Xipeng Artificial Intelligence I.2; I.2.11; I.2.10; H.5.2 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. |
| title | EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience |
| topic | Artificial Intelligence I.2; I.2.11; I.2.10; H.5.2 |
| url | https://arxiv.org/abs/2601.15876 |