ScreenExplorer: Training a Vision-Language Model for Diverse Exploration in Open GUI World
This work addresses the challenge of building AGI systems in GUI environments for AI researchers, though it appears incremental as it builds on existing VLM and LLM methods.
The paper tackled the problem of GUI agents failing to generalize to novel environments by introducing ScreenExplorer, a vision-language model trained with a curiosity reward function and experience distillation, which showed better environmental adaptation and sustained exploration in open GUI settings.
The rapid progress of large language models (LLMs) has sparked growing interest in building Artificial General Intelligence (AGI) within Graphical User Interface (GUI) environments. However, existing GUI agents based on LLMs or vision-language models (VLMs) often fail to generalize to novel environments and rely heavily on manually curated, diverse datasets. To overcome these limitations, we introduce ScreenExplorer, a VLM trained via Group Relative Policy Optimization(GRPO) in real, dynamic, and open-ended GUI environments. Innovatively, we introduced a world-model-based curiosity reward function to help the agent overcome the cold-start phase of exploration. Additionally, distilling experience streams further enhances the model's exploration capabilities. Our training framework enhances model exploration in open GUI environments, with trained models showing better environmental adaptation and sustained exploration compared to static deployment models. Our findings offer a scalable pathway toward AGI systems with self-improving capabilities in complex interactive settings.