# Hybrid Computer-Use Agents

The authors introduce CUA-SWE, a benchmark, interactive development environment, and evaluation pipeline spanning 105 tasks across Web, Game, DevOps, and Mobile, in which an agent edits code, runs commands, operates the running software, and inspects screenshots within a single task, with task-specific deterministic tests deciding the outcome; comparing code-only and hybrid CUA conditions across frontier models, GPT-6-Astra reaches the highest four-domain mean of 59.9%, and every frontier model in the four-domain comparison achieves higher aggregate success with hybrid access, with gains concentrated on tasks whose requirements must be recovered from application materials such as drawings, service contracts, or graphical reference cards.

The authors introduce CUA-SWE, a benchmark, interactive development environment, and evaluation pipeline spanning 105 tasks across Web, Game, DevOps, and Mobile, in which an agent edits code, runs commands, operates the running software, and inspects screenshots within a single task, with task-specific deterministic tests deciding the outcome; comparing code-only and hybrid CUA conditions across frontier models, GPT-6-Astra reaches the highest four-domain mean of 59.9%, and every frontier model in the four-domain comparison achieves higher aggregate success with hybrid access, with gains concentrated on tasks whose requirements must be recovered from application materials such as drawings, service contracts, or graphical reference cards.

This work introduces RecreationWorld, a framework, and RecreationBench, a benchmark: given a running reference application, an agent must discover its behavior and deliver a buildable, runnable recreation, with reproducible environments on Ubuntu, macOS, Windows, Android, and Web plus a unified GUI-and-coding harness, automatic scoring by reference-derived hidden programmatic and visual assertions, and 35,000 filtered recreation trajectories for training; evaluation shows GPT-6 Astra leading at 58.1% overall while passing all programmatic tests on just 2.8% of tasks, and recreations reproducing static interface structure more reliably than interactions and computed outputs.

This work introduces RecreationWorld, a framework, and RecreationBench, a benchmark: given a running reference application, an agent must discover its behavior and deliver a buildable, runnable recreation, with reproducible environments on Ubuntu, macOS, Windows, Android, and Web plus a unified GUI-and-coding harness, automatic scoring by reference-derived hidden programmatic and visual assertions, and 35,000 filtered recreation trajectories for training; evaluation shows GPT-6 Astra leading at 58.1% overall while passing all programmatic tests on just 2.8% of tasks, and recreations reproducing static interface structure more reliably than interactions and computed outputs.