diff --git a/libs/langchain/langchain/agents/json_chat/base.py b/libs/langchain/langchain/agents/json_chat/base.py
index 7a70c0bf4c6..70228ce2735 100644
--- a/libs/langchain/langchain/agents/json_chat/base.py
+++ b/libs/langchain/langchain/agents/json_chat/base.py
@@ -1,4 +1,4 @@
-from typing import Sequence
+from typing import List, Sequence, Union
 
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.prompts.chat import ChatPromptTemplate
@@ -15,7 +15,7 @@ def create_json_chat_agent(
     llm: BaseLanguageModel,
     tools: Sequence[BaseTool],
     prompt: ChatPromptTemplate,
-    stop_sequence: bool = True,
+    stop_sequence: Union[bool, List[str]] = True,
     tools_renderer: ToolsRenderer = render_text_description,
 ) -> Runnable:
     """Create an agent that uses JSON to format its logic, build for Chat Models.
@@ -24,7 +24,11 @@ def create_json_chat_agent(
         llm: LLM to use as the agent.
         tools: Tools this agent has access to.
         prompt: The prompt to use. See Prompt section below for more.
-        stop_sequence: Adds a stop token of "Observation:" to avoid hallucinates. 
+        stop_sequence: bool or list of str.
+            If True, adds a stop token of "Observation:" to avoid hallucinates. 
+            If False, does not add a stop token.
+            If a list of str, uses the provided list as the stop tokens.
+            
             Default is True. You may to set this to False if the LLM you are using
             does not support stop sequences.
         tools_renderer: This controls how the tools are converted into a string and
@@ -158,7 +162,8 @@ def create_json_chat_agent(
         tool_names=", ".join([t.name for t in tools]),
     )
     if stop_sequence:
-        llm_to_use = llm.bind(stop=["\nObservation"])
+        stop = ["\nObservation"] if stop_sequence is True else stop_sequence
+        llm_to_use = llm.bind(stop=stop)
     else:
         llm_to_use = llm
 
diff --git a/libs/langchain/langchain/agents/react/agent.py b/libs/langchain/langchain/agents/react/agent.py
index 7c0f70bbd4a..531b4c74a05 100644
--- a/libs/langchain/langchain/agents/react/agent.py
+++ b/libs/langchain/langchain/agents/react/agent.py
@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Optional, Sequence
+from typing import List, Optional, Sequence, Union
 
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.prompts import BasePromptTemplate
@@ -19,6 +19,8 @@ def create_react_agent(
     prompt: BasePromptTemplate,
     output_parser: Optional[AgentOutputParser] = None,
     tools_renderer: ToolsRenderer = render_text_description,
+    *,
+    stop_sequence: Union[bool, List[str]] = True,
 ) -> Runnable:
     """Create an agent that uses ReAct prompting.
 
@@ -29,6 +31,13 @@ def create_react_agent(
         output_parser: AgentOutputParser for parse the LLM output.
         tools_renderer: This controls how the tools are converted into a string and
             then passed into the LLM. Default is `render_text_description`.
+        stop_sequence: bool or list of str.
+            If True, adds a stop token of "Observation:" to avoid hallucinates.
+            If False, does not add a stop token.
+            If a list of str, uses the provided list as the stop tokens.
+
+            Default is True. You may to set this to False if the LLM you are using
+            does not support stop sequences.
 
     Returns:
         A Runnable sequence representing an agent. It takes as input all the same input
@@ -108,7 +117,11 @@ def create_react_agent(
         tools=tools_renderer(list(tools)),
         tool_names=", ".join([t.name for t in tools]),
     )
-    llm_with_stop = llm.bind(stop=["\nObservation"])
+    if stop_sequence:
+        stop = ["\nObservation"] if stop_sequence is True else stop_sequence
+        llm_with_stop = llm.bind(stop=stop)
+    else:
+        llm_with_stop = llm
     output_parser = output_parser or ReActSingleInputOutputParser()
     agent = (
         RunnablePassthrough.assign(
diff --git a/libs/langchain/langchain/agents/structured_chat/base.py b/libs/langchain/langchain/agents/structured_chat/base.py
index 735160f639d..8eaf409490c 100644
--- a/libs/langchain/langchain/agents/structured_chat/base.py
+++ b/libs/langchain/langchain/agents/structured_chat/base.py
@@ -1,5 +1,5 @@
 import re
-from typing import Any, List, Optional, Sequence, Tuple
+from typing import Any, List, Optional, Sequence, Tuple, Union
 
 from langchain_core._api import deprecated
 from langchain_core.agents import AgentAction
@@ -155,6 +155,8 @@ def create_structured_chat_agent(
     tools: Sequence[BaseTool],
     prompt: ChatPromptTemplate,
     tools_renderer: ToolsRenderer = render_text_description_and_args,
+    *,
+    stop_sequence: Union[bool, List[str]] = True,
 ) -> Runnable:
     """Create an agent aimed at supporting tools with multiple inputs.
 
@@ -162,6 +164,13 @@ def create_structured_chat_agent(
         llm: LLM to use as the agent.
         tools: Tools this agent has access to.
         prompt: The prompt to use. See Prompt section below for more.
+        stop_sequence: bool or list of str.
+            If True, adds a stop token of "Observation:" to avoid hallucinates.
+            If False, does not add a stop token.
+            If a list of str, uses the provided list as the stop tokens.
+
+            Default is True. You may to set this to False if the LLM you are using
+            does not support stop sequences.
         tools_renderer: This controls how the tools are converted into a string and
             then passed into the LLM. Default is `render_text_description`.
 
@@ -273,7 +282,11 @@ def create_structured_chat_agent(
         tools=tools_renderer(list(tools)),
         tool_names=", ".join([t.name for t in tools]),
     )
-    llm_with_stop = llm.bind(stop=["Observation"])
+    if stop_sequence:
+        stop = ["\nObservation"] if stop_sequence is True else stop_sequence
+        llm_with_stop = llm.bind(stop=stop)
+    else:
+        llm_with_stop = llm
 
     agent = (
         RunnablePassthrough.assign(
diff --git a/libs/langchain/langchain/agents/xml/base.py b/libs/langchain/langchain/agents/xml/base.py
index 572b50a8ca7..370c48ba022 100644
--- a/libs/langchain/langchain/agents/xml/base.py
+++ b/libs/langchain/langchain/agents/xml/base.py
@@ -112,6 +112,8 @@ def create_xml_agent(
     tools: Sequence[BaseTool],
     prompt: BasePromptTemplate,
     tools_renderer: ToolsRenderer = render_text_description,
+    *,
+    stop_sequence: Union[bool, List[str]] = True,
 ) -> Runnable:
     """Create an agent that uses XML to format its logic.
 
@@ -123,6 +125,13 @@ def create_xml_agent(
             `agent_scratchpad`: contains previous agent actions and tool outputs.
         tools_renderer: This controls how the tools are converted into a string and
             then passed into the LLM. Default is `render_text_description`.
+        stop_sequence: bool or list of str.
+            If True, adds a stop token of "</tool_input>" to avoid hallucinates.
+            If False, does not add a stop token.
+            If a list of str, uses the provided list as the stop tokens.
+
+            Default is True. You may to set this to False if the LLM you are using
+            does not support stop sequences.
 
     Returns:
         A Runnable sequence representing an agent. It takes as input all the same input
@@ -201,7 +210,12 @@ def create_xml_agent(
     prompt = prompt.partial(
         tools=tools_renderer(list(tools)),
     )
-    llm_with_stop = llm.bind(stop=["</tool_input>"])
+
+    if stop_sequence:
+        stop = ["</tool_input>"] if stop_sequence is True else stop_sequence
+        llm_with_stop = llm.bind(stop=stop)
+    else:
+        llm_with_stop = llm
 
     agent = (
         RunnablePassthrough.assign(