diff --git a/docs/source/manual/arch_lang/circuit_library.rst b/docs/source/manual/arch_lang/circuit_library.rst
index 4ec803f99..0e515b84b 100644
--- a/docs/source/manual/arch_lang/circuit_library.rst
+++ b/docs/source/manual/arch_lang/circuit_library.rst
@@ -53,6 +53,7 @@ Here, we focus these common syntax and we will detail special syntax in :ref:`ci
     <input_buffer exist="<string>" circuit_model_name="<string>"/>
     <output_buffer exist="<string>" circuit_model_name="<string>"/>
     <pass_gate_logic type="<string>" circuit_model_name="<string>"/>
+    <last_stage_pass_gate_logic type="<string>" circuit_model_name="<string>"/>
     <port type="<string>" prefix="<string>" lib_name="<string>" size="<int>" default_val="<int>" circuit_model_name="<string>" mode_select="<bool>" is_global="<bool>" is_set="<bool>" is_reset="<bool>" is_config_enable="<bool>"/>
     <!-- more ports -->
   </circuit_model>
@@ -129,12 +130,16 @@ Input and Output Buffers
 Pass Gate Logic
 ^^^^^^^^^^^^^^^
 
+.. note:: pass-gate logic are used in building multiplexers and LUTs.
+
 .. option:: <pass_gate_logic circuit_model_name="<string>"/>
 
   - ``circuit_model_name="<string>"`` Specify the name of the circuit model which is used to implement pass-gate logic, the type of specified circuit model should be ``pass_gate``.
 
-.. note:: pass-gate logic are used in building multiplexers and LUTs.
 
+.. option:: <last_stage_pass_gate_logic circuit_model_name="<string>"/>
+
+  - ``circuit_model_name="<string>"`` Specify the name of the circuit model which is used to implement the pass-gate logic at last stage of multiplexer, the type of specified circuit model should be ``pass_gate``. The type of the pass-gate logic circuit model must be a standard cell MUX2!
 
 .. _circuit_library_circuit_port:
 
diff --git a/docs/source/manual/arch_lang/circuit_model_examples.rst b/docs/source/manual/arch_lang/circuit_model_examples.rst
index 94f1d5e02..a2a64715c 100644
--- a/docs/source/manual/arch_lang/circuit_model_examples.rst
+++ b/docs/source/manual/arch_lang/circuit_model_examples.rst
@@ -619,6 +619,14 @@ This example shows:
 
 Standard Cell Multiplexer
 `````````````````````````
+.. _fig_stdcellmux:
+
+.. figure:: ./figures/stdcellmux.png
+   :width: 100%
+   :alt: Examples of MUX built with standard cells
+
+   An example of a multiplexer built with standard cells: (a) all the MUX2 are the same; (b) the MUX2 at the last stage is a different one 
+
 .. code-block:: xml
 
   <circuit_model type="mux" name="mux_stdcell" prefix="mux_stdcell">
@@ -631,12 +639,34 @@ Standard Cell Multiplexer
     <port type="sram" prefix="sram" size="3"/>
   </circuit_model>
 
-This example shows:
+This example shows (see an illustative example in :numref:`fig_stdcellmux`(a)):
   - A tree-like 4-input CMOS multiplexer built by the standard cell ``MUX2``
   - All the inputs will be buffered using the circuit model ``inv1x``
   - All the outputs will be buffered using the circuit model ``tapbuf4``
   - The multiplexer will have 4 inputs and 3 SRAMs to control which datapath to propagate
 
+Alternatively, user can specify a different standard cell MUX2 at the last stage.
+
+.. code-block:: xml
+
+  <circuit_model type="mux" name="mux_stdcell" prefix="mux_stdcell">
+    <design_technology type="cmos" structure="tree"/>
+    <input_buffer exist="on" circuit_model_name="inv1x"/>
+    <output_buffer exist="on" circuit_model_name="tapdrive4"/>
+    <pass_gate_logic circuit_model_name="MUX2"/>
+    <last_stage_pass_gate_logic circuit_model_name="MUX2D2"/>
+    <port type="input" prefix="in" size="4"/>
+    <port type="output" prefix="out" size="1"/>
+    <port type="sram" prefix="sram" size="3"/>
+  </circuit_model>
+
+This example shows (see an illustative example in :numref:`fig_stdcellmux`(b)):
+  - A tree-like 4-input CMOS multiplexer built by the standard cell ``MUX2``
+  - The last stage A tree-like 4-input CMOS multiplexer built by the standard cell ``MUX2``
+  - All the inputs will be buffered using the circuit model ``inv1x``
+  - All the outputs will be buffered using the circuit model ``tapbuf4``
+  - The multiplexer will have 4 inputs and 3 SRAMs to control which datapath to propagate
+
 .. _circuit_model_mux_multilevel_example:
 
 Multi-level Multiplexer
diff --git a/docs/source/manual/arch_lang/figures/stdcellmux.png b/docs/source/manual/arch_lang/figures/stdcellmux.png
new file mode 100644
index 000000000..d2d08c7b1
Binary files /dev/null and b/docs/source/manual/arch_lang/figures/stdcellmux.png differ