diff --git a/libs/prebuilt/langgraph/prebuilt/chat_agent_executor.py b/libs/prebuilt/langgraph/prebuilt/chat_agent_executor.py
index e4c189902..a8597d9f0 100644
--- a/libs/prebuilt/langgraph/prebuilt/chat_agent_executor.py
+++ b/libs/prebuilt/langgraph/prebuilt/chat_agent_executor.py
@@ -1,4 +1,3 @@
-import functools
 import inspect
 from typing import (
     Any,
@@ -141,27 +140,6 @@ def _get_prompt_runnable(prompt: Optional[Prompt]) -> Runnable:
     return prompt_runnable
 
 
-def _convert_modifier_to_prompt(func: F) -> F:
-    """Decorator that converts state_modifier kwarg to prompt kwarg."""
-
-    @functools.wraps(func)
-    def wrapper(*args: Any, **kwargs: Any) -> Any:
-        prompt = kwargs.get("prompt")
-        state_modifier = kwargs.pop("state_modifier", None)
-        if sum(p is not None for p in (prompt, state_modifier)) > 1:
-            raise ValueError(
-                "Expected only one of (prompt, state_modifier), got multiple values"
-            )
-
-        if state_modifier is not None:
-            prompt = state_modifier
-
-        kwargs["prompt"] = prompt
-        return func(*args, **kwargs)
-
-    return cast(F, wrapper)
-
-
 def _should_bind_tools(model: LanguageModelLike, tools: Sequence[BaseTool]) -> bool:
     if isinstance(model, RunnableSequence):
         model = next(
@@ -260,7 +238,6 @@ def _validate_chat_history(
     raise ValueError(error_message)
 
 
-@_convert_modifier_to_prompt
 def create_react_agent(
     model: Union[str, LanguageModelLike],
     tools: Union[Sequence[Union[BaseTool, Callable]], ToolNode],
diff --git a/libs/prebuilt/tests/test_react_agent.py b/libs/prebuilt/tests/test_react_agent.py
index d2d6960d3..df092675d 100644
--- a/libs/prebuilt/tests/test_react_agent.py
+++ b/libs/prebuilt/tests/test_react_agent.py
@@ -141,39 +141,26 @@ async def test_no_prompt_async(checkpointer_name: str) -> None:
             assert saved.pending_writes == []
 
 
-def test_passing_two_modifiers():
-    model = FakeToolCallingModel()
-
-    with pytest.raises(ValueError):
-        create_react_agent(model, [], state_modifier="Foo", prompt="Bar")
-
-
 def test_system_message_prompt():
     prompt = SystemMessage(content="Foo")
-    for agent in (
-        create_react_agent(FakeToolCallingModel(), [], prompt=prompt),
-        create_react_agent(FakeToolCallingModel(), [], state_modifier=prompt),
-    ):
-        inputs = [HumanMessage("hi?")]
-        response = agent.invoke({"messages": inputs})
-        expected_response = {
-            "messages": inputs + [AIMessage(content="Foo-hi?", id="0", tool_calls=[])]
-        }
-        assert response == expected_response
+    agent = create_react_agent(FakeToolCallingModel(), [], prompt=prompt)
+    inputs = [HumanMessage("hi?")]
+    response = agent.invoke({"messages": inputs})
+    expected_response = {
+        "messages": inputs + [AIMessage(content="Foo-hi?", id="0", tool_calls=[])]
+    }
+    assert response == expected_response
 
 
 def test_string_prompt():
     prompt = "Foo"
-    for agent in (
-        create_react_agent(FakeToolCallingModel(), [], prompt=prompt),
-        create_react_agent(FakeToolCallingModel(), [], state_modifier=prompt),
-    ):
-        inputs = [HumanMessage("hi?")]
-        response = agent.invoke({"messages": inputs})
-        expected_response = {
-            "messages": inputs + [AIMessage(content="Foo-hi?", id="0", tool_calls=[])]
-        }
-        assert response == expected_response
+    agent = create_react_agent(FakeToolCallingModel(), [], prompt=prompt)
+    inputs = [HumanMessage("hi?")]
+    response = agent.invoke({"messages": inputs})
+    expected_response = {
+        "messages": inputs + [AIMessage(content="Foo-hi?", id="0", tool_calls=[])]
+    }
+    assert response == expected_response
 
 
 def test_callable_prompt():
@@ -181,16 +168,11 @@ def test_callable_prompt():
         modified_message = f"Bar {state['messages'][-1].content}"
         return [HumanMessage(content=modified_message)]
 
-    for agent in (
-        create_react_agent(FakeToolCallingModel(), [], prompt=prompt),
-        create_react_agent(FakeToolCallingModel(), [], state_modifier=prompt),
-    ):
-        inputs = [HumanMessage("hi?")]
-        response = agent.invoke({"messages": inputs})
-        expected_response = {
-            "messages": inputs + [AIMessage(content="Bar hi?", id="0")]
-        }
-        assert response == expected_response
+    agent = create_react_agent(FakeToolCallingModel(), [], prompt=prompt)
+    inputs = [HumanMessage("hi?")]
+    response = agent.invoke({"messages": inputs})
+    expected_response = {"messages": inputs + [AIMessage(content="Bar hi?", id="0")]}
+    assert response == expected_response
 
 
 async def test_callable_prompt_async():
@@ -198,16 +180,11 @@ async def test_callable_prompt_async():
         modified_message = f"Bar {state['messages'][-1].content}"
         return [HumanMessage(content=modified_message)]
 
-    for agent in (
-        create_react_agent(FakeToolCallingModel(), [], prompt=prompt),
-        create_react_agent(FakeToolCallingModel(), [], state_modifier=prompt),
-    ):
-        inputs = [HumanMessage("hi?")]
-        response = await agent.ainvoke({"messages": inputs})
-        expected_response = {
-            "messages": inputs + [AIMessage(content="Bar hi?", id="0")]
-        }
-        assert response == expected_response
+    agent = create_react_agent(FakeToolCallingModel(), [], prompt=prompt)
+    inputs = [HumanMessage("hi?")]
+    response = await agent.ainvoke({"messages": inputs})
+    expected_response = {"messages": inputs + [AIMessage(content="Bar hi?", id="0")]}
+    assert response == expected_response
 
 
 def test_runnable_prompt():
@@ -215,16 +192,11 @@ def test_runnable_prompt():
         lambda state: [HumanMessage(content=f"Baz {state['messages'][-1].content}")]
     )
 
-    for agent in (
-        create_react_agent(FakeToolCallingModel(), [], prompt=prompt),
-        create_react_agent(FakeToolCallingModel(), [], state_modifier=prompt),
-    ):
-        inputs = [HumanMessage("hi?")]
-        response = agent.invoke({"messages": inputs})
-        expected_response = {
-            "messages": inputs + [AIMessage(content="Baz hi?", id="0")]
-        }
-        assert response == expected_response
+    agent = create_react_agent(FakeToolCallingModel(), [], prompt=prompt)
+    inputs = [HumanMessage("hi?")]
+    response = agent.invoke({"messages": inputs})
+    expected_response = {"messages": inputs + [AIMessage(content="Baz hi?", id="0")]}
+    assert response == expected_response
 
 
 @pytest.mark.parametrize("version", REACT_TOOL_CALL_VERSIONS)