🌍 UI-Simulator: LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training

License Python Build Stars

πŸ”— Paper link: Link

🌐 Website: https://ui-simulator.notion.site/llms-as-scalable-digital-world-simulator

πŸ“š Github: https://github.com/WadeYin9712/UI-Simulator

πŸ“§ Contact: [email protected], [email protected]


Model Card for Model ID

This is the Step1 agent trained with retrieval-augmented UI-Simulator with UI-Simulator-Grow scaling paradigm. It is trained to solve AndroidWorld tasks.

Uses

We provide a script for loading the model and run AndroidWorld evaluation here.

Downloads last month
16
Safetensors
Model size
8B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for UI-Simulator/UI_Simulator_Grow_Android_Step1

Base model

Qwen/Qwen2.5-7B
Finetuned
(2816)
this model

Dataset used to train UI-Simulator/UI_Simulator_Grow_Android_Step1