WildAWM synthesizes environments for computer-use agent training
The open-source pipeline made 341 long-horizon tasks; GPT-6-Astra solved 60%, and two trained Qwen models improved on eight benchmarks.
Stories per day · 30 days
1 RSS
Relatedagent-training3computer-use-agents3qwen2benchmark1gui1open-source-models1osworld1softwaregym1wildawm1
3 stories, newest first · one card per story
Stories tagged #synthetic-environments
WildAWM synthesizes computer-use agent environments with open models
It yields 341 tasks that can exceed 100 steps; GPT-6-Astra solves 60%, and Qwen models trained only there improve on eight benchmarks.
SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments
SoftwareGym's 182 synthetic apps lift a computer-use agent to 56.97% OSWorld Pass@3.