diff --git a/docs/references/http_api_reference.md b/docs/references/http_api_reference.md
index a9611906c..74133ef18 100644
--- a/docs/references/http_api_reference.md
+++ b/docs/references/http_api_reference.md
@@ -5,7 +5,7 @@ slug: /http_api_reference
 
 # HTTP API
 
-A complete reference for RAGFlow's RESTful API. Before proceeding, please ensure you [have your RAGFlow API key ready for authentication](../guides/models/llm_api_key_setup.md).
+A complete reference for RAGFlow's RESTful API. Before proceeding, please ensure you [have your RAGFlow API key ready for authentication](../develop/acquire_ragflow_api_key.md).
 
 ---
 
@@ -191,13 +191,13 @@ curl --request POST \
 
 ##### Request Parameters
 
-- `model` (*Body parameter*) `string`, *Required*
+- `model` (*Body parameter*) `string`, *Required*  
   The model used to generate the response. The server will parse this automatically, so you can set it to any value for now.
 
-- `messages` (*Body parameter*) `list[object]`, *Required*
+- `messages` (*Body parameter*) `list[object]`, *Required*  
   A list of historical chat messages used to generate the response. This must contain at least one message with the `user` role.
 
-- `stream` (*Body parameter*) `boolean`
+- `stream` (*Body parameter*) `boolean`  
   Whether to receive the response as a stream. Set this to `false` explicitly if you prefer to receive the entire response in one go instead of as a stream.
 
 #### Response
@@ -2675,7 +2675,7 @@ curl --request POST \
 
 - `agent_id`: (*Path parameter*)  
   The ID of the associated agent.
-- `user_id`: (*Filter parameter*)
+- `user_id`: (*Filter parameter*)  
   The optional user-defined ID for parsing docs (especially images) when creating a session while uploading files.
 
 #### Response
@@ -2755,7 +2755,7 @@ Success:
                             "mode": "conversational",
                             "outputs": {},
                             "prologue": "Hi! I'm your assistant. What can I do for you?",
-                            "tips": "Please fill up the form"
+                            "tips": "Please fill in the form"
                         }
                     },
                     "upstream": []
@@ -2912,17 +2912,17 @@ Asks a specified agent a question to start an AI-powered conversation.
 - Body:
   - `"question"`: `string`
   - `"stream"`: `boolean`
-  - `"session_id"`: `string`(optional)
-  - `"inputs"`: `object`(optional)
-  - `"user_id"`: `string`(optional)
+  - `"session_id"`: `string` (optional)
+  - `"inputs"`: `object` (optional)
+  - `"user_id"`: `string` (optional)
 
 :::info IMPORTANT
-You can include custom parameters in the request body, but first ensure they are defined in the [Begin](../guides/agent/agent_component_reference/begin.mdx) agent component.
+You can include custom parameters in the request body, but first ensure they are defined in the [Begin](../guides/agent/agent_component_reference/begin.mdx) component.
 :::
 
 ##### Request example
 
-- If the **Begin** component does not take parameters.
+- If the **Begin** component does not take parameters:
 
 ```bash
 curl --request POST \
@@ -2936,7 +2936,7 @@ curl --request POST \
      }'
 ```
 
-- If the **Begin** component takes parameters.  
+- If the **Begin** component takes parameters, include their values in the body of `"inputs"` as follows:  
 
 ```bash
 curl --request POST \
diff --git a/docs/references/python_api_reference.md b/docs/references/python_api_reference.md
index f0ad981a3..07fd92bbf 100644
--- a/docs/references/python_api_reference.md
+++ b/docs/references/python_api_reference.md
@@ -5,7 +5,7 @@ slug: /python_api_reference
 
 # Python API
 
-A complete reference for RAGFlow's Python APIs. Before proceeding, please ensure you [have your RAGFlow API key ready for authentication](../guides/models/llm_api_key_setup.md).
+A complete reference for RAGFlow's Python APIs. Before proceeding, please ensure you [have your RAGFlow API key ready for authentication](../develop/acquire_ragflow_api_key.md).
 
 :::tip NOTE
 Run the following command to download the Python SDK:
diff --git a/docs/release_notes.md b/docs/release_notes.md
index 0c0f42be4..3baaa495a 100644
--- a/docs/release_notes.md
+++ b/docs/release_notes.md
@@ -22,6 +22,36 @@ The embedding models included in a full edition are:
 These two embedding models are optimized specifically for English and Chinese, so performance may be compromised if you use them to embed documents in other languages.
 :::
 
+## v0.20.2 (Ongoing🔨)
+
+Released on August ??, 2025.
+
+### Improvements
+
+- Revamps the user interface for the **Datasets**, **Chat**, and **Search** pages.  
+- Search: Supports creating search apps tailored to various business scenarios
+- Chat: Supports comparing answer performance of up to three chat model settings on a single **Chat** page.
+- Agent:  
+  - Implements a toggle in the **Agent** component to enable or disable citation.  
+  - Introduces a drag-and-drop method for creating components.  
+- Documentation: Corrects inaccuracies in the API reference.
+
+### New Agent templates
+
+- Report Agent: A template for generating summary reports in internal question-answering scenarios, supporting the display of tables and formulae.  [#9427](https://github.com/infiniflow/ragflow/pull/9427)
+
+### Fixed issues
+
+- Predefined opening greeting in the **Agent** component was missing during conversations.  
+- An automatic line break issue in the prompt editor.  
+- A memory leak issue caused by PyPDF. [#9469](https://github.com/infiniflow/ragflow/pull/9469)
+
+### API changes
+
+#### Deprecated
+
+[Create session with agent](./references/http_api_reference.md#create-session-with-agent)
+
 ## v0.20.1
 
 Released on August 8, 2025.
@@ -182,7 +212,7 @@ From this release onwards, if you still see RAGFlow's responses being cut short
 
 - Unable to add models via Ollama/Xinference, an issue introduced in v0.17.1.
 
-### Related APIs
+### API changes
 
 #### HTTP APIs
 
@@ -243,7 +273,7 @@ The following is a screenshot of a conversation that integrates Deep Research:
 
 ![Image](https://github.com/user-attachments/assets/165b88ff-1f5d-4fb8-90e2-c836b25e32e9)
 
-### Related APIs
+### API changes
 
 #### HTTP APIs
 
@@ -318,7 +348,7 @@ This release fixes the following issues:
 - Using the **Table** parsing method results in information loss.
 - Miscellaneous API issues.
 
-### Related APIs
+### API changes
 
 #### HTTP APIs
 
@@ -354,7 +384,7 @@ Released on December 18, 2024.
 - Upgrades the Document Layout Analysis model in DeepDoc.
 - Significantly enhances the retrieval performance when using [Infinity](https://github.com/infiniflow/infinity) as document engine.
 
-### Related APIs
+### API changes
 
 #### HTTP APIs
 
@@ -411,7 +441,7 @@ This approach eliminates the need to manually update **service_config.yaml** aft
 Ensure that you [upgrade **both** your code **and** Docker image to this release](https://ragflow.io/docs/dev/upgrade_ragflow#upgrade-ragflow-to-the-most-recent-officially-published-release) before trying this new approach.
 :::
 
-### Related APIs
+### API changes
 
 #### HTTP APIs
 
@@ -570,7 +600,7 @@ While we also test RAGFlow on ARM64 platforms, we do not maintain RAGFlow Docker
 If you are on an ARM platform, follow [this guide](./develop/build_docker_image.mdx) to build a RAGFlow Docker image.
 :::
 
-### Related APIs
+### API changes
 
 #### HTTP API
 
@@ -591,7 +621,7 @@ Released on May 21, 2024.
 - Supports monitoring of system components, including Elasticsearch, MySQL, Redis, and MinIO.
 - Supports disabling **Layout Recognition** in the GENERAL chunking method to reduce file chunking time.
 
-### Related APIs
+### API changes
 
 #### HTTP API