diff --git a/README.md b/README.md
index fc7e2a1a731..90faa2358fa 100644
--- a/README.md
+++ b/README.md
@@ -132,7 +132,6 @@ Quickstart examples:
 - [Quickstart (JAX)](https://github.com/adap/flower/tree/main/examples/quickstart-jax)
 - [Quickstart (MONAI)](https://github.com/adap/flower/tree/main/examples/quickstart-monai)
 - [Quickstart (scikit-learn)](https://github.com/adap/flower/tree/main/examples/sklearn-logreg-mnist)
-- [Quickstart (XGBoost)](https://github.com/adap/flower/tree/main/examples/xgboost-quickstart)
 - [Quickstart (Android [TFLite])](https://github.com/adap/flower/tree/main/examples/android)
 - [Quickstart (iOS [CoreML])](https://github.com/adap/flower/tree/main/examples/ios)
 - [Quickstart (MLX)](https://github.com/adap/flower/tree/main/examples/quickstart-mlx)
@@ -144,8 +143,8 @@ Other [examples](https://github.com/adap/flower/tree/main/examples):
 - [PyTorch: From Centralized to Federated](https://github.com/adap/flower/tree/main/examples/pytorch-from-centralized-to-federated)
 - [Vertical FL](https://github.com/adap/flower/tree/main/examples/vertical-fl)
 - [Federated Finetuning of OpenAI's Whisper](https://github.com/adap/flower/tree/main/examples/whisper-federated-finetuning)
+- [Federated Finetuning of Large Language Model](https://github.com/adap/flower/tree/main/examples/fedllm-finetune)
 - [Federated Finetuning of a Vision Transformer](https://github.com/adap/flower/tree/main/examples/vit-finetune)
-- [Comprehensive XGBoost](https://github.com/adap/flower/tree/main/examples/xgboost-comprehensive)
 - [Advanced Flower with TensorFlow/Keras](https://github.com/adap/flower/tree/main/examples/advanced-tensorflow)
 - [Advanced Flower with PyTorch](https://github.com/adap/flower/tree/main/examples/advanced-pytorch)
 - Single-Machine Simulation of Federated Learning Systems ([PyTorch](https://github.com/adap/flower/tree/main/examples/simulation-pytorch)) ([Tensorflow](https://github.com/adap/flower/tree/main/examples/simulation-tensorflow))
diff --git a/examples/fedllm-finetune/README.md b/examples/fedllm-finetune/README.md
index 108fdcf687b..7b71e928b2b 100644
--- a/examples/fedllm-finetune/README.md
+++ b/examples/fedllm-finetune/README.md
@@ -28,6 +28,7 @@ This will create a new directory called `fedllm-finetune` containing the followi
 -- dataset.py          <- Dataset and tokenizer build
 -- utils.py            <- Utility functions
 -- test.py             <- Test pre-trained model
+-- app.py              <- ServerApp/ClientApp for Flower-Next
 -- conf/config.yaml    <- Configuration file
 -- requirements.txt    <- Example dependencies
 ```
@@ -42,8 +43,6 @@ pip install -r requirements.txt
 
 ## Run LLM Fine-tuning
 
-### Run with `start_simulation()`
-
 With an activated Python environment, run the example with default config values. The config is in `conf/config.yaml` and is loaded automatically.
 
 ```bash
@@ -61,31 +60,6 @@ python main.py model.name="openlm-research/open_llama_7b_v2" model.quantization=
 python main.py num_rounds=50 fraction_fit.fraction_fit=0.25
 ```
 
-### Run with Flower Next (demo)
-
-We conduct a 2-client setting to demonstrate how to run federated LLM fine-tuning with Flower Next.
-Please follow the steps below:
-
-1. Start the long-running Flower server (SuperLink)
-   ```bash
-   flower-superlink --insecure
-   ```
-2. Start the long-running Flower client (SuperNode)
-   ```bash
-   # In a new terminal window, start the first long-running Flower client:
-   flower-client-app app:client1 --insecure
-   ```
-   ```bash
-   # In another new terminal window, start the second long-running Flower client:
-   flower-client-app app:client2 --insecure
-   ```
-3. Run the Flower App
-   ```bash
-   # With both the long-running server (SuperLink) and two clients (SuperNode) up and running,
-   # we can now run the actual Flower App:
-   flower-server-app app:server --insecure
-   ```
-
 ## Expected Results
 
 ![](_static/train_loss_smooth.png)
@@ -138,3 +112,28 @@ Finally, end your day with a relaxing visit to the London Eye, the tallest Ferri
 
 The [`Vicuna`](https://huggingface.co/lmsys/vicuna-13b-v1.1) template we used in this example is for a chat assistant.
 The generated answer is expected to be a multi-turn conversations. Feel free to try more interesting questions!
+
+## Run with Flower Next (preview)
+
+We conduct a 2-client setting to demonstrate how to run federated LLM fine-tuning with Flower Next.
+Please follow the steps below:
+
+1. Start the long-running Flower server (SuperLink)
+   ```bash
+   flower-superlink --insecure
+   ```
+2. Start the long-running Flower client (SuperNode)
+   ```bash
+   # In a new terminal window, start the first long-running Flower client:
+   flower-client-app app:client1 --insecure
+   ```
+   ```bash
+   # In another new terminal window, start the second long-running Flower client:
+   flower-client-app app:client2 --insecure
+   ```
+3. Run the Flower App
+   ```bash
+   # With both the long-running server (SuperLink) and two clients (SuperNode) up and running,
+   # we can now run the actual Flower App:
+   flower-server-app app:server --insecure
+   ```