← Sunday, October 18, 2026AgentsPaper

Cowork-Gym synthesizes 64.9K interactive work environments for agent training

huggingface.co by Anni Zou et al. Editor score 8/10

Cowork-Gym uses a build-execute-revise loop and stateful user simulation to generate 64.9K environments; its post-trained models improve by 8.7, 6.4 and 4.1 points across six benchmarks. The scale and measured gains make it a useful example of building realistic training environments for tool-using agents.

What
Cowork-Gym synthesizes interactive work environments through a build-execute-revise loop that uses execution evidence and review feedback to validate and repair them.
Method
A stateful user simulator responds to agent actions through dialogue and direct edits to the shared workspace.
Why it matters
The framework produced 64.9K environments across 14 application scenarios for training and evaluating agents in changing, tool-rich workspaces.
executes validates and repairs reviews direct edits build-execute-r…loop review feedback stateful usersimulator executionevidence shared workspace
The synthesis loop uses execution evidence and review feedback, while a simulator edits the shared workspace. Sketched from the article's own text.

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.

Your note

Private to you. Stored in this browser, and synced to your account when you are signed in.