diff --git a/python/llm/example/CPU/Application/hf-agent/README.md b/python/llm/example/CPU/Applications/hf-agent/README.md
similarity index 72%
rename from python/llm/example/CPU/Application/hf-agent/README.md
rename to python/llm/example/CPU/Applications/hf-agent/README.md
index fb346147ea3d..d0712999aba6 100644
--- a/python/llm/example/CPU/Application/hf-agent/README.md
+++ b/python/llm/example/CPU/Applications/hf-agent/README.md
@@ -1,20 +1,12 @@
 # BigDL-LLM Transformers INT4 Optimization for HuggingFace Transformers Agent
-In this directory, you will find examples on how you could apply BigDL-LLM INT4 optimizations on HuggingFace Transformers Agent. For illustration purposes, we utilize the [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) as the reference model.
+In this example, we apply low-bit optimizations to [HuggingFace Transformers Agents](https://huggingface.co/docs/transformers/transformers_agents) using BigDL-LLM, which allows LLMs to use tools such as image generation, image captioning, text summarization, etc.
 
-## 0. Requirements
-To run the examples, we recommend using Intel® Xeon® processors (server), or >= 12th Gen Intel® Core™ processor (client).
+For illustration purposes, we utilize the [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) as the reference model. We use [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) to create an agent. Then we ask the agent to generate the caption for an image from coco dataset, i.e. [demo.jpg](https://cocodataset.org/#explore?id=264959)
 
-For OS, BigDL-LLM supports Ubuntu 20.04 or later, CentOS 7 or later, and Windows 10/11.
+## 0. Requirements
+To run this example with BigDL-LLM, we have some recommended requirements for your machine, please refer to [here](https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/CPU/HF-Transformers-AutoModels/Model#recommended-requirements) for more information.
 
-## Best Known Configuration on Linux
-For better performance, it is recommended to set environment variables on Linux with the help of BigDL-Nano:
-```bash
-pip install bigdl-nano
-source bigdl-nano-init
-```
 
-## Example: Run an agent using `run()` API
-In the example [run_agent.py](./run_agent.py), we show a basic use case of using `run()` API to run an agent, which uses Vicuna model with BigDL-LLM INT4 optimizations.
 ### 1. Install
 We suggest using conda to manage environment:
 ```bash
@@ -61,6 +53,8 @@ numactl -C 0-47 -m 0 python ./run_agent.py
 #### [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5)
 ```log
 Image path: demo.jpg
+== Prompt ==
+Generate a caption for the 'image'
 ==Explanation from the agent==
 I will use the following tool: `image_captioner` to generate a caption for the image.
 
diff --git a/python/llm/example/CPU/Application/hf-agent/demo.jpg b/python/llm/example/CPU/Applications/hf-agent/demo.jpg
similarity index 100%
rename from python/llm/example/CPU/Application/hf-agent/demo.jpg
rename to python/llm/example/CPU/Applications/hf-agent/demo.jpg
diff --git a/python/llm/example/CPU/Application/hf-agent/run_agent.py b/python/llm/example/CPU/Applications/hf-agent/run_agent.py
similarity index 92%
rename from python/llm/example/CPU/Application/hf-agent/run_agent.py
rename to python/llm/example/CPU/Applications/hf-agent/run_agent.py
index 807cf2dc1754..98fca0c5d4d5 100644
--- a/python/llm/example/CPU/Application/hf-agent/run_agent.py
+++ b/python/llm/example/CPU/Applications/hf-agent/run_agent.py
@@ -44,5 +44,8 @@
     agent = LocalAgent(model, tokenizer)
 
     # Generate results
+    prompt = "Generate a caption for the 'image'"
     print(f"Image path: {args.image_path}")
-    print(agent.run("Generate a caption for the 'image'", image=image))
+    print('==', 'Prompt', '==')
+    print(prompt)
+    print(agent.run(prompt, image=image))
diff --git a/python/llm/example/CPU/README.md b/python/llm/example/CPU/README.md
index 4b4b3b87a3bd..b6be45cd2767 100644
--- a/python/llm/example/CPU/README.md
+++ b/python/llm/example/CPU/README.md
@@ -6,7 +6,7 @@ This folder contains examples of running BigDL-LLM on Intel CPU:
 - [PyTorch-Models](PyTorch-Models): running any PyTorch model on BigDL-LLM (with "one-line code change")
 - [Native-Models](Native-Models): converting & running LLM in `llama`/`chatglm`/`bloom`/`gptneox`/`starcoder` model family using native (cpp) implementation
 - [LangChain](LangChain): running LangChain applications on BigDL-LLM
-- [Application](Application): running Transformers applications on BigDl-LLM
+- [Applications](Applications): running Transformers applications on BigDl-LLM
 
 ## System Support
 **Hardware**: