WildAWM training general intelligence agents
The story so far
The Qwen model, after training in synthetic environments synthesized by WildAWM, shows significant performance improvement in cross-distribution benchmarks. WildAWM interacts to synthesize controllable computer environments and tasks, supporting graphical interfaces, model context protocol services, and command-line interfaces, fully based on open-source models, and introduces an execution-based level mechanism to address solvability, difficulty maintenance, and validator reliability issues in task synthesis.
AI-written from the reports · Updated 27 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersAgent World Model in the Wild: Computer-Use Agent Environment Synthesis
WildAWM enhances the generalization performance of general agents in web, CLI, and GUI benchmark tests through interactive synthesis of controllable computer environments and tasks. The system supports graphical interfaces, model context protocol services, and command-line interfaces, fully based on open-source models, and introduces an execution-based level mechanism to address solvability, difficulty maintenance, and verifier reliability issues in task synthesis. After training the Qwen model in the WildAWM synthetic environment, it achieved significant improvements in 8 cross-distribution benchmark tests.