# RecreationWorld：面向混合计算机使用智能体的可扩展可验证环境发布

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-18 08:00
- AIHOT 分数：55
- AIHOT 链接：https://aihot.news/items/cmuam2cqg0o30ro5tkvatsfs9
- 原文链接：https://arxiv.org/abs/2609.22000

## AI 摘要

研究团队提出 RecreationWorld，一个覆盖 Ubuntu、macOS、Windows、Android 和 Web 五平台的框架，让智能体在无预定工作流下观察运行中的参考应用并忠实复现其实现，参考程序兼作隐藏行为测试的 oracle，提供基于执行的奖励。

## 正文

Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Real digital work requires both, interleaved rather than stacked end to end. We study hybrid CUAs that autonomously decide when to explore an interface, implement software, and run and visually verify their artifacts. We introduce RecreationWorld, a five-platform framework built around recreation: given a running reference, an agent must discover its behavior and build a faithful implementation with no prescribed workflow.

RecreationWorld provides reproducible environments on Ubuntu, macOS, Windows, Android, and Web, plus a unified harness with native GUI control and coding tools. The running reference serves as an oracle for hidden behavioral tests, providing execution-grounded rewards. We scale trajectory generation with high-quality open-source applications. Models trained on these trajectories improve across five out-of-distribution coding and hybrid computer-use benchmarks and more frequently verify their rendered outputs, providing evidence of transfer beyond recreation.

For held-out evaluation, we introduce RecreationBench, comprising 250 diverse tasks across domains and platforms. Reference-grounded programmatic and visual assertions cover action-conditioned outcomes at multiple interaction depths; each is validated on the reference and by human reviewers before the suite is frozen for automatic scoring. GPT-6 Astra leads at 58.1% overall, but passes all programmatic tests on just 2.8% of tasks. Agents reproduce static interface structure more reliably than interactions and computed outputs, while generated applications remain smaller and more monolithic than their references.

We release the benchmark, environments, and test suites.