nielsr HF Staff commited on
Commit
0a47148
·
verified ·
1 Parent(s): 257258a

Add paper link and abstract to model card

Browse files

This PR updates the model card to include a direct link to the research paper, [MobiAgent: A Systematic Framework for Customizable Mobile Agents](https://huggingface.co/papers/2509.00531), providing users with easier access to the foundational research behind the model. It also adds the paper's abstract for more comprehensive documentation.

Files changed (1) hide show
  1. README.md +9 -5
README.md CHANGED
@@ -1,23 +1,27 @@
1
  ---
 
2
  license: apache-2.0
3
  pipeline_tag: image-text-to-text
4
  tags:
5
  - multimodal
6
  - gui
7
- library_name: transformers
8
  ---
9
 
10
  # MobiMind-Decider-7B Model
11
 
12
- This is the Decider Model of [MobiAgent](https://github.com/IPADS-SAI/MobiAgent) with 7B parameters, capable of high-level GUI interaction decision in GUI agent task execution.
 
 
 
 
13
 
14
  ## About MobiAgent
15
 
16
  **MobiAgent** is a powerful mobile agent system including:
17
 
18
- * **An agent model family**: MobiMind
19
- * **An agent acceleration framework**: AgentRR
20
- * **An agent benchmark**: MobiFlow
21
 
22
  **System Architecture:**
23
 
 
1
  ---
2
+ library_name: transformers
3
  license: apache-2.0
4
  pipeline_tag: image-text-to-text
5
  tags:
6
  - multimodal
7
  - gui
 
8
  ---
9
 
10
  # MobiMind-Decider-7B Model
11
 
12
+ This is the Decider Model of [MobiAgent](https://github.com/IPADS-SAI/MobiAgent) with 7B parameters, as presented in the paper [MobiAgent: A Systematic Framework for Customizable Mobile Agents](https://huggingface.co/papers/2509.00531), capable of high-level GUI interaction decision in GUI agent task execution.
13
+
14
+ ## Paper Abstract
15
+
16
+ With the rapid advancement of Vision-Language Models (VLMs), GUI-based mobile agents have emerged as a key development direction for intelligent mobile systems. However, existing agent models continue to face significant challenges in real-world task execution, particularly in terms of accuracy and efficiency. To address these limitations, we propose MobiAgent, a comprehensive mobile agent system comprising three core components: the MobiMind-series agent models, the AgentRR acceleration framework, and the MobiFlow benchmarking suite. Furthermore, recognizing that the capabilities of current mobile agents are still limited by the availability of high-quality data, we have developed an AI-assisted agile data collection pipeline that significantly reduces the cost of manual annotation. Compared to both general-purpose LLMs and specialized GUI agent models, MobiAgent achieves state-of-the-art performance in real-world mobile scenarios.
17
 
18
  ## About MobiAgent
19
 
20
  **MobiAgent** is a powerful mobile agent system including:
21
 
22
+ * **An agent model family**: MobiMind
23
+ * **An agent acceleration framework**: AgentRR
24
+ * **An agent benchmark**: MobiFlow
25
 
26
  **System Architecture:**
27