add figure to explain AReaLite components

README.md

@@ -27,8 +27,8 @@ like how you enjoy real-world milk tea (cheers).
   code. This allows users to build their own **agentic** and **RLVR** training workflows
   with minimal effort.
 - 🔥 **Asynchronous RL**: With algorithm-system co-design, AReaL supports fully
-  asynchronous RL for **the fastest training speed**! Experimental support for multi-turn
+  asynchronous RL for **the fastest training speed**! Experimental support for
-  agentic RL is also provided.
+  multi-turn agentic RL is also provided.
 - 🛠️ **Open & Reproducible**: We continuously release _all code, datasets, and training
   recipes_ for RL training of LLMs.
 - 🚀 **Scalability**: AReaL can seamlessly adapt to different computational resource
@@ -69,7 +69,7 @@ New highlights in AReaLite:
 - Instead of the *system-centric* architecture in old AReaL, AReaLite follows an
   **AI-centric** API design that aims to provide the following key features:
 
-  - **Light-weight** & **easy to write** algorithm and training workflow customization.
+  - **Light-weight** & **easy-to-write** algorithm and training workflow customization.
   - **Easy to scale up** without knowing system and infrastructure details.
   - **Adaptable and plugable:** Smooth to integrate with other modern AI applications.
 
@@ -106,8 +106,8 @@ Our training scripts will automatically download the dataset (openai/gsm8k) and
 python3 -m arealite.launcher.local examples/arealite/gsm8k_grpo.py --config examples/arealite/configs/gsm8k_grpo.yaml
 ```
 
-On a Ray cluster with 2 nodes & 8 GPUs each node, runs (Remember to change paths in the YAML
+On a Ray cluster with 2 nodes & 8 GPUs each node, runs (Remember to change paths in the
-file to your own shared storage):
+YAML file to your own shared storage):
 
 ```
 python3 -m arealite.launcher.ray examples/arealite/gsm8k_grpo.py --config examples/arealite/configs/gsm8k_grpo.yaml \

arealite/README.md

@@ -12,9 +12,9 @@ understand, and develop with effectively. The primary issue stems from its
 *system-centric* rather than *AI-centric* architecture and API design. An *AI-centric*
 design aims to provide three key features:
 
-- **Light-weight & focused customization:** Users can implement their algorithms and
+- **Light-weight & easy-to-write customization:** Users can implement their algorithms
-  training workflows with minimal and concentrated code, often in just a few files or
+  and training workflows with minimal and concentrated code, often in just a few files
-  even a single file.
+  or even a single file.
 - **Easy to scale up:** Experiments can be scaled up seamlessly without requiring
   knowledge of underlying system or infrastructure details.
 - **Adaptable and plugable:** Users is free to integrate the system with code or APIs
@@ -80,6 +80,16 @@ arealite/
 
 ### Component Overview
 
+The AReaLite codebase is structured into four distinct layers: the API layer, backend
+layer, customization layer, and entry point layer. As illustrated in the figure below,
+workflow and algorithm customization logic resides in separate layers above the backend.
+We prioritize keeping the entry point and customization layers clean and intuitive,
+isolating them from the complex backend implementation. With AReaLite, users can define
+their custom training workflows and algorithms entirely within a single entry point
+file.
+
+![arealite-layers](../assets/arealite_layers.png)
+
 #### 1. API Layer (`api/`)
 
 The API layer establishes clean contracts between components through abstract interfaces