---
license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen2.5-VL-3B-Instruct
tags:
- gui
- agent
---

# InfiGUI-R1-3B

This repository contains the model from the [InfiGUI-R1](https://arxiv.org/abs/2504.14239) paper. The model is based on `Qwen2.5-VL-3B-Instruct` and trained using the proposed Actor2Reasoner framework, enhanced through reinforcement learning to improve its planning and reflection capabilities for GUI tasks.