├── images
    ├── test_img.png
    └── InfiGUIAgent_logo.jpg
└── README.md


/images/test_img.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/InfiXAI/InfiGUIAgent/HEAD/images/test_img.png


--------------------------------------------------------------------------------
/images/InfiGUIAgent_logo.jpg:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/InfiXAI/InfiGUIAgent/HEAD/images/InfiGUIAgent_logo.jpg


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | <h1 align="center">
 2 | <img src="images/InfiGUIAgent_logo.jpg" width="100" alt="ToRA" />
 3 | <br>
 4 | InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
 5 | </h1>
 6 | 
 7 | <br>
 8 | <div align="center" style="margin: 20px 0; display: flex; justify-content: center; gap: 15px;"> | 
 9 |     <a href="https://b7277.github.io/InfiGUIAgent.github.io/" style="padding: 8px 15px; background-color: #2F4F4F; color: white; border-radius: 5px; text-decoration: none; transition: all 0.3s;">🏠 Homepage</a> | 
10 |     <a href="https://arxiv.org/abs/2501.04575" style="padding: 8px 15px; background-color: #B22222; color: white; border-radius: 5px; text-decoration: none; transition: all 0.3s;">📚 Arxiv</a> | 
11 |     <a href="https://huggingface.co/papers/2501.04575" style="padding: 8px 15px; background-color: #FFD700; color: black; border-radius: 5px; text-decoration: none; transition: all 0.3s;">🤗 Paper</a> | 
12 |     <a href="https://huggingface.co/collections/Reallm-Labs/infiguiagent-67a4e4bdfbba9036a1700d97" style="padding: 8px 15px; background-color: #6495ED; color: white; border-radius: 5px; text-decoration: none; transition: all 0.3s;">🤗 Collection</a> | 
13 | </div>
14 | <br>
15 | 
16 | This is the repo for the paper "[InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection](https://huggingface.co/papers/2501.04575)". In this work, we develop a multimodal large language model-based GUI agent that enables enhanced task automation on computing devices. Our agent is trained through a two-stage supervised fine-tuning approach that focuses on fundamental GUI understanding skills and advanced reasoning capabilities, where we integrate hierarchical reasoning and expectation-reflection reasoning to enable native reasoning abilities in GUI interactions.
17 | 
18 | ## 🔥  News
19 | - 🔥[2025/5/15] Our paper "[OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use](https://os-agent-survey.github.io/)" is accepted by *ACL 2025*.
20 | - 🔥[2025/4/19] Our paper "[InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners](https://arxiv.org/abs/2504.14239)" released. More information can be found in [the repository](https://github.com/Reallm-Labs/InfiGUI-R1).
21 | - 🔥[2025/1/9] Our paper "[InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection](https://arxiv.org/abs/2501.04575)" released.
22 | - 🔥[2024/12/12] Our paper "[OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use](https://os-agent-survey.github.io/)" released.
23 | - [2024/4/2] Our paper "[InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks](https://infiagent.github.io/)" is accepted by *ICML 2024*.
24 | 
25 | ## InfiGUIAgent
26 | We are in the process of uploading key artifacts from our paper to our 🤗 [Hugging Face Collection](https://huggingface.co/collections/Reallm-Labs/infiguiagent-67a4e4bdfbba9036a1700d97).
27 | 
28 | Regarding the full model release, due to licensing restrictions on portions of our training data from third-party sources, we are currently sanitizing the dataset and retraining/refining the final model to ensure full compliance while maintaining performance.
29 | 
30 | Stay tuned for updates! 🔜
31 | 


--------------------------------------------------------------------------------