# RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

arXiv: https://arxiv.org/abs/2609.22000 · HTML: https://mlsanity.com/paper/2609.22000/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 28 of 28)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://mlsanity.com/paper/2410.23218/) (2024)
- [Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models](https://mlsanity.com/paper/2312.06585/) (2023)
- [UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2509.02544/) (2025)
- [SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?](https://mlsanity.com/paper/2410.03859/) (2024)
- [Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering](https://mlsanity.com/paper/2403.03163/) (2024)
- [Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs](https://mlsanity.com/paper/2406.20098/) (2024)
- [WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch](https://mlsanity.com/paper/2505.03733/) (2025)
- [ProgramBench: Can Language Models Rebuild Programs From Scratch?](https://mlsanity.com/paper/2605.03546/) (2026)
- [Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping](https://mlsanity.com/paper/2411.03292/) (2024)
- [DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation](https://mlsanity.com/paper/2506.06251/) (2025)
- [WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs](https://mlsanity.com/paper/2404.06369/) (2024)
- [InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training](https://mlsanity.com/paper/2601.04126/) (2026)
- [Gym-Anything: Turn any Software into an Agent Environment](https://mlsanity.com/paper/2604.06126/) (2026)
- [CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents](https://mlsanity.com/paper/2605.25624/) (2026)
- [GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?](https://mlsanity.com/paper/2606.17861/) (2026)
- [AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines](https://mlsanity.com/paper/2602.14296/) (2026)
- [GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training](https://mlsanity.com/paper/2602.14093/) (2026)
- [Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification](https://mlsanity.com/paper/2603.26648/) (2026)
- [You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation](https://mlsanity.com/paper/2508.14104/) (2025)
- [Safe and Scalable Web Agent Learning via Recreated Websites](https://mlsanity.com/paper/2603.10505/) (2026)
- [Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents](https://mlsanity.com/paper/2607.28227/) (2026)
- [WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces](https://mlsanity.com/paper/2606.09426/) (2026)
- [Qwen-CUA: Native Computer Use for (almost) Everything](https://mlsanity.com/paper/2608.02352/) (2026)
- [SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL](https://mlsanity.com/paper/2607.11185/) (2026)
- [PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions](https://mlsanity.com/paper/2606.14832/) (2026)
- [AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?](https://mlsanity.com/paper/2510.07740/) (2025)
- [StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents](https://mlsanity.com/paper/2607.22798/) (2026)

## Built on by (most cited first, 1 of 1)

- [HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents](https://mlsanity.com/paper/2609.38008/) (2026)

## Abstract (arXiv)

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.