跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-08AI 評分48

SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments

SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments

AI 導讀

SoftwareGym 提出一套自動化流程,合成具多元介面、可執行功能及經運行時驗證的 GUI 軟件環境,以擴展電腦操作智能體(CUA)訓練。研究團隊合成了涵蓋十二個類別的 182 個應用程式,平均 GUI 任務通過率為 91.5%,並建立包含 120 項任務的 SoftwareGym-Bench。

正文

Published on Oct 8

Authors:

,

,

,

,

,

Abstract

Computer-use agents (CUAs) are rapidly improving, yet synthesizing diverse and reliable software environments at scale remains challenging. Native application environments require substantial construction and integration effort, which limits application coverage and increases the risk of application-specific overfitting. Browser-hosted environments provide limited interaction depth and workflow complexity. These limitations motivate SoftwareGym, an automated pipeline for synthesizing GUI software environments with diverse interfaces, executable functionality, and runtime-verified behavior. It generates structurally diverse designs, realizes them as runnable applications, and uses GUI evaluation with iterative repair to ensure functional reliability. Using SoftwareGym, we synthesize 182 applications across twelve categories and achieve a mean GUI task pass rate of 91.5%. We construct SoftwareGym-Bench, a 120-task evaluation suite spanning the same twelve categories, and use trajectories collected from these environments for CUA training. The resulting model improves Pass@3 from 41.39% to 56.97% on the strictly out-of-domain OSWorld benchmark and achieves 40.0% on SoftwareGym-Bench. These results demonstrate the potential of synthesized software environments as scalable and transferable supervision for CUA training.

View arXiv page View PDF GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.12611

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.12611 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.12611 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.12611 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co