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

• URL: http://arxiv.org/abs/2601.15876v2
• Date: Fri, 23 Jan 2026 08:52:00 GMT
• Title: EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
• Authors: Taofeng Xue, Chong Peng, Mianqiu Huang, Linsen Guo, Tiancheng Han, Haozhe Wang, Jianing Wang, Xiaocheng Zhang, Xin Yang, Dengchang Zhao, Jinrui Ding, Xiandi Ma, Yuchen Xie, Peng Pei, Xunliang Cai, Xipeng Qiu,
• Abstract summary: We introduce EvoCUA, a native computer use agentic model.<n>Unlike static imitation, EvoCUA integrates data generation and policy optimization into a self-sustaining evolutionary cycle.<n>EvoCUA significantly outperforms the previous best open-source model, OpenCUA-72B.
• Score: 44.734653745434834
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots [68.29056647487519]
  Embodied AI is fueled by high-fidelity simulation and large-scale data collection.<n>However, this scaling capability remains bottlenecked by a reliance on labor-intensive manual oversight.<n>We introduce textscEmboCoach-Bench, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies.
  arXiv  Detail & Related papers  (2026-01-29T11:33:49Z)
• From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions [70.72279728350763]
  Self-evolving agentic artificial intelligence (AI) offers a new paradigm for future wireless systems.<n>Unlike static AI models, self-evolving agents embed an autonomous evolution cycle that updates models, tools, and in response to environmental dynamics.<n>This paper presents a comprehensive overview of self-evolving agentic AI, highlighting its layered architecture, life cycle, and key techniques.
  arXiv  Detail & Related papers  (2025-10-07T05:45:25Z)
• SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience [71.82719117238307]
  We propose SEAgent, an agentic self-evolving framework enabling computer-use agents to evolve through interactions with unfamiliar software.<n>We validate the effectiveness of SEAgent across five novel software environments within OS-World.<n>Our approach achieves a significant improvement of 23.2% in success rate, from 11.3% to 34.5%, over a competitive open-source CUA.
  arXiv  Detail & Related papers  (2025-08-06T17:58:46Z)
• Evolutionary Generative Optimization: Towards Fully Data-Driven Evolutionary Optimization via Generative Learning [41.44929681213813]
  We propose a fully data-driven framework empowered by generative learning.<n>EvoGO streamlines the evolutionary optimization process into three stages: data preparation, model training, and population generation.<n>Experiments on numerical benchmarks, classical control problems, and high-dimensional robotic tasks demonstrate that EvoGO consistently converges within merely 10 generations.
  arXiv  Detail & Related papers  (2025-08-01T07:17:57Z)
• ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution [77.86222359025011]
  We propose ToolACE-DEV, a self-improving framework for tool learning.<n>First, we decompose the tool-learning objective into sub-tasks that enhance basic tool-making and tool-using abilities.<n>We then introduce a self-evolving paradigm that allows lightweight models to self-improve, reducing reliance on advanced LLMs.
  arXiv  Detail & Related papers  (2025-05-12T12:48:30Z)
• DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal [55.13854171147104]
  Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development.<n>We present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents.<n>We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2.
  arXiv  Detail & Related papers  (2025-03-18T14:02:59Z)
• An Innovative Next Activity Prediction Approach Using Process Entropy and DAW-Transformer [7.139735602624267]
  This paper proposes an entropy-driven model selection approach and DAW-Transformer to integrate all attributes with a dynamic window for better accuracy.<n>Experiments were conducted on six public datasets, and the performance was evaluated with process entropy.
  arXiv  Detail & Related papers  (2025-02-14T22:02:00Z)
• Trackable Agent-based Evolution Models at Wafer Scale [0.0]
  We focus on the problem of extracting phylogenetic information from agent-based evolution on the 850,000 processor Cerebras Wafer Scale Engine (WSE) We present an asynchronous island-based genetic algorithm (GA) framework for WSE hardware. We validate phylogenetic reconstructions from these trials and demonstrate their suitability for inference of underlying evolutionary conditions.
  arXiv  Detail & Related papers  (2024-04-16T19:24:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.