Update README.md

README.md

@@ -23,7 +23,7 @@ pipeline_tag: image-text-to-text
 
 ## Overview
 
-**AgentCPM-GUI** is an open-source on-device LLM agent model jointly developed by [THUNLP](https://nlp.csai.tsinghua.edu.cn) and [ModelBest](https://modelbest.cn/en). Built on [MiniCPM-V](https://github.com/OpenBMB/MiniCPM-V) with 8 billion parameters, it accepts smartphone screenshots as input and autonomously executes user-specified tasks. 
+**AgentCPM-GUI** is an open-source on-device LLM agent model jointly developed by [THUNLP](https://nlp.csai.tsinghua.edu.cn), Renmin University of China and [ModelBest](https://modelbest.cn/en). Built on [MiniCPM-V](https://github.com/OpenBMB/MiniCPM-V) with 8 billion parameters, it accepts smartphone screenshots as input and autonomously executes user-specified tasks. 
 
 Key features include:
 
@@ -42,7 +42,7 @@ https://github.com/user-attachments/assets/5472a659-cd71-4bce-a181-0981129c6a81
 
 ```bash
 git clone https://github.com/OpenBMB/AgentCPM-GUI
-cd MiniCPM-Agent
+cd AgentCPM-GUI
 conda create -n gui_agent python=3.11
 conda activate gui_agent
 pip install -r requirements.txt
@@ -225,7 +225,7 @@ print(response)
 
 ## Fine-tuning
 
-Source code for SFT and RFT training is provided — see [SFT](sft/readme.md) and [RFT](rft/readme.md).
+Source code for SFT and RFT training is provided — see [GitHub](https://github.com/OpenBMB/AgentCPM-GUI).
 
 ## Performance Evaluation
 
@@ -261,7 +261,9 @@ Source code for SFT and RFT training is provided — see [SFT](sft/readme.md) an
 
 > \*Different train/test splits
 
-All evaluation data and code are open-sourced — see [here](eval) for details.
+TM and EM stand for the **Type Match** and **Exact Match**, respectively. All evaluation data and code are open-sourced — see [here](eval) for details.
+
+All evaluation data and code are open-sourced — see [here](https://github.com/OpenBMB/AgentCPM-GUI/tree/main/eval) for details.
 
 ## Evaluation Data