Paper page - Cowork-Gym: Synthesizing Interactive Work Environments at Scale

Source: https://huggingface.co/papers/2610.17670 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Cowork-Gym synthesizes collaborative agent environments via iterative validation and trains Qwen models that substantially improve agentic benchmark performance.

Cowork agents navigate dependencies across tools and files while adapting to changing user requirements and edits to shared workspaces. Scaling such environments requires maintaining consistency among task objectives, executable resources, user behavior, and success criteria. We introduce Cowork-Gym, a framework that synthesizes Cowork environments through abuild-execute-revise loopthat uses execution evidence and review feedback to validate and repair generated environments. To capture realistic Cowork dynamics, astateful user simulatorresponds to the agent’s actions through dialogue and direct edits to the shared workspace. We synthesize 64.9K environments across 14 application scenarios and use them to post-train 9B, 27B, and 35B-A3B Qwen models withsupervised fine-tuning,reinforcement learning, andon-policy distillation. Averaged across six agentic benchmarks, these models outperform their corresponding base checkpoints by 8.7, 6.4, and 4.1 points, respectively. Ours-27B ranks second overall among the evaluated models and achieves the highest average scores on PawBench and ClawEval, outperforming models with over 100B total parameters on both benchmarks.

View arXiv pageView PDFProject pageAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.17670 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.17670 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.17670 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.