Skip to content

Multi-agent supervisor

Supervisor is a multi-agent architecture where specialized agents are coordinated by a central supervisor agent. The supervisor agent controls all communication flow and task delegation, making decisions about which agent to invoke based on the current context and task requirements.

In this tutorial, you will build a supervisor system with two agents — a research and a math expert. By the end of the tutorial you will:

  1. Build specialized research and math agents
  2. Build a supervisor for orchestrating them with the prebuilt langgraph-supervisor
  3. Build a supervisor from scratch
  4. Implement advanced task delegation

diagram

Setup

First, let's install required packages and set our API keys

pip install -U langgraph langgraph-supervisor langchain-tavily "langchain[openai]"

import getpass
import os


def _set_if_undefined(var: str):
    if not os.environ.get(var):
        os.environ[var] = getpass.getpass(f"Please provide your {var}")


_set_if_undefined("OPENAI_API_KEY")
_set_if_undefined("TAVILY_API_KEY")

Set up LangSmith for LangGraph development

Sign up for LangSmith to quickly spot issues and improve the performance of your LangGraph projects. LangSmith lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph — read more about how to get started here.

1. Create worker agents

First, let's create our specialized worker agents — research agent and math agent:

  • Research agent will have access to a web search tool using Tavily API
  • Math agent will have access to simple math tools (add, multiply, divide)

Research agent

For web search, we will use TavilySearch tool from langchain-tavily:

API Reference: TavilySearch

from langchain_tavily import TavilySearch

web_search = TavilySearch(max_results=3)
web_search_results = web_search.invoke("who is the mayor of NYC?")

print(web_search_results["results"][0]["content"])

Find events, attractions, deals, and more at nyctourism.com Skip Main Navigation Menu The Official Website of the City of New York Text Size Powered by Translate SearchSearch Primary Navigation The official website of NYC Home NYC Resources NYC311 Office of the Mayor Events Connect Jobs Search Office of the Mayor | Mayor's Bio | City of New York Secondary Navigation MayorBiographyNewsOfficials Eric L. Adams 110th Mayor of New York City Mayor Eric Adams has served the people of New York City as an NYPD officer, State Senator, Brooklyn Borough President, and now as the 110th Mayor of the City of New York. Mayor Eric Adams has served the people of New York City as an NYPD officer, State Senator, Brooklyn Borough President, and now as the 110th Mayor of the City of New York. He gave voice to a diverse coalition of working families in all five boroughs and is leading the fight to bring back New York City’s economy, reduce inequality, improve public safety, and build a stronger, healthier city that delivers for all New Yorkers. As the representative of one of the nation’s largest counties, Eric fought tirelessly to grow the local economy, invest in schools, reduce inequality, improve public safety, and advocate for smart policies and better government that delivers for all New Yorkers.
To create individual worker agents, we will use LangGraph's prebuilt agent.

API Reference: create_react_agent

from langgraph.prebuilt import create_react_agent

research_agent = create_react_agent(
    model="openai:gpt-4.1",
    tools=[web_search],
    prompt=(
        "You are a research agent.\n\n"
        "INSTRUCTIONS:\n"
        "- Assist ONLY with research-related tasks, DO NOT do any math\n"
        "- After you're done with your tasks, respond to the supervisor directly\n"
        "- Respond ONLY with the results of your work, do NOT include ANY other text."
    ),
    name="research_agent",
)

Let's run the agent to verify that it behaves as expected.

We'll use pretty_print_messages helper to render the streamed agent outputs nicely 
from langchain_core.messages import convert_to_messages


def pretty_print_message(message, indent=False):
    pretty_message = message.pretty_repr(html=True)
    if not indent:
        print(pretty_message)
        return

    indented = "\n".join("\t" + c for c in pretty_message.split("\n"))
    print(indented)


def pretty_print_messages(update, last_message=False):
    is_subgraph = False
    if isinstance(update, tuple):
        ns, update = update
        # skip parent graph updates in the printouts
        if len(ns) == 0:
            return

        graph_id = ns[-1].split(":")[0]
        print(f"Update from subgraph {graph_id}:")
        print("\n")
        is_subgraph = True

    for node_name, node_update in update.items():
        update_label = f"Update from node {node_name}:"
        if is_subgraph:
            update_label = "\t" + update_label

        print(update_label)
        print("\n")

        messages = convert_to_messages(node_update["messages"])
        if last_message:
            messages = messages[-1:]

        for m in messages:
            pretty_print_message(m, indent=is_subgraph)
        print("\n")


for chunk in research_agent.stream(
    {"messages": [{"role": "user", "content": "who is the mayor of NYC?"}]}
):
    pretty_print_messages(chunk)

Update from node agent:


================================== Ai Message ==================================
Name: research_agent
Tool Calls:
  tavily_search (call_U748rQhQXT36sjhbkYLSXQtJ)
 Call ID: call_U748rQhQXT36sjhbkYLSXQtJ
  Args:
    query: current mayor of New York City
    search_depth: basic


Update from node tools:


================================= Tool Message =================================
Name: tavily_search

{"query": "current mayor of New York City", "follow_up_questions": null, "answer": null, "images": [], "results": [{"title": "List of mayors of New York City - Wikipedia", "url": "https://en.wikipedia.org/wiki/List_of_mayors_of_New_York_City", "content": "The mayor of New York City is the chief executive of the Government of New York City, as stipulated by New York City's charter.The current officeholder, the 110th in the sequence of regular mayors, is Eric Adams, a member of the Democratic Party.. During the Dutch colonial period from 1624 to 1664, New Amsterdam was governed by the Director of New Netherland.", "score": 0.9039154, "raw_content": null}, {"title": "Office of the Mayor | Mayor's Bio | City of New York - NYC.gov", "url": "https://www.nyc.gov/office-of-the-mayor/bio.page", "content": "Mayor Eric Adams has served the people of New York City as an NYPD officer, State Senator, Brooklyn Borough President, and now as the 110th Mayor of the City of New York. He gave voice to a diverse coalition of working families in all five boroughs and is leading the fight to bring back New York City's economy, reduce inequality, improve", "score": 0.8405867, "raw_content": null}, {"title": "Eric Adams - Wikipedia", "url": "https://en.wikipedia.org/wiki/Eric_Adams", "content": "Eric Leroy Adams (born September 1, 1960) is an American politician and former police officer who has served as the 110th mayor of New York City since 2022. Adams was an officer in the New York City Transit Police and then the New York City Police Department (NYPD) for more than 20 years, retiring at the rank of captain.He served in the New York State Senate from 2006 to 2013, representing the", "score": 0.77731717, "raw_content": null}], "response_time": 1.81}


Update from node agent:


================================== Ai Message ==================================
Name: research_agent

The current mayor of New York City is Eric Adams.

Math agent

For math agent tools we will use vanilla Python functions:

def add(a: float, b: float):
    """Add two numbers."""
    return a + b


def multiply(a: float, b: float):
    """Multiply two numbers."""
    return a * b


def divide(a: float, b: float):
    """Divide two numbers."""
    return a / b


math_agent = create_react_agent(
    model="openai:gpt-4.1",
    tools=[add, multiply, divide],
    prompt=(
        "You are a math agent.\n\n"
        "INSTRUCTIONS:\n"
        "- Assist ONLY with math-related tasks\n"
        "- After you're done with your tasks, respond to the supervisor directly\n"
        "- Respond ONLY with the results of your work, do NOT include ANY other text."
    ),
    name="math_agent",
)

Let's run the math agent:

for chunk in math_agent.stream(
    {"messages": [{"role": "user", "content": "what's (3 + 5) x 7"}]}
):
    pretty_print_messages(chunk)

Update from node agent:


================================== Ai Message ==================================
Name: math_agent
Tool Calls:
  add (call_p6OVLDHB4LyCNCxPOZzWR15v)
 Call ID: call_p6OVLDHB4LyCNCxPOZzWR15v
  Args:
    a: 3
    b: 5


Update from node tools:


================================= Tool Message =================================
Name: add

8.0


Update from node agent:


================================== Ai Message ==================================
Name: math_agent
Tool Calls:
  multiply (call_EoaWHMLFZAX4AkajQCtZvbli)
 Call ID: call_EoaWHMLFZAX4AkajQCtZvbli
  Args:
    a: 8
    b: 7


Update from node tools:


================================= Tool Message =================================
Name: multiply

56.0


Update from node agent:


================================== Ai Message ==================================
Name: math_agent

56

2. Create supervisor with langgraph-supervisor

To implement out multi-agent system, we will use create_supervisor from the prebuilt langgraph-supervisor library:

API Reference: create_supervisor | init_chat_model

from langgraph_supervisor import create_supervisor
from langchain.chat_models import init_chat_model

supervisor = create_supervisor(
    model=init_chat_model("openai:gpt-4.1"),
    agents=[research_agent, math_agent],
    prompt=(
        "You are a supervisor managing two agents:\n"
        "- a research agent. Assign research-related tasks to this agent\n"
        "- a math agent. Assign math-related tasks to this agent\n"
        "Assign work to one agent at a time, do not call agents in parallel.\n"
        "Do not do any work yourself."
    ),
    add_handoff_back_messages=True,
    output_mode="full_history",
).compile()

from IPython.display import display, Image

display(Image(supervisor.get_graph().draw_mermaid_png()))

Let's now run it with a query that requires both agents:

  • research agent will look up the necessary GDP information
  • math agent will perform division to find the percentage of NY state GDP, as requested

for chunk in supervisor.stream(
    {
        "messages": [
            {
                "role": "user",
                "content": "find US and New York state GDP in 2024. what % of US GDP was New York state?",
            }
        ]
    },
):
    pretty_print_messages(chunk, last_message=True)

final_message_history = chunk["supervisor"]["messages"]

Update from node supervisor:


================================= Tool Message =================================
Name: transfer_to_research_agent

Successfully transferred to research_agent


Update from node research_agent:


================================= Tool Message =================================
Name: transfer_back_to_supervisor

Successfully transferred back to supervisor


Update from node supervisor:


================================= Tool Message =================================
Name: transfer_to_math_agent

Successfully transferred to math_agent


Update from node math_agent:


================================= Tool Message =================================
Name: transfer_back_to_supervisor

Successfully transferred back to supervisor


Update from node supervisor:


================================== Ai Message ==================================
Name: supervisor

In 2024, the US GDP was $29.18 trillion and New York State's GDP was $2.297 trillion. New York State accounted for approximately 7.87% of the total US GDP in 2024.

3. Create supervisor from scratch

Let's now implement this same multi-agent system from scratch. We will need to:

  1. Set up how the supervisor communicates with individual agents
  2. Create the supervisor agent
  3. Combine supervisor and worker agents into a single multi-agent graph.

Set up agent communication

We will need to define a way for the supervisor agent to communicate with the worker agents. A common way to implement this in multi-agent architectures is using handoffs, where one agent hands off control to another. Handoffs allow you to specify:

  • destination: target agent to transfer to
  • payload: information to pass to that agent

We will implement handoffs via handoff tools and give these tools to the supervisor agent: when the supervisor calls these tools, it will hand off control to a worker agent, passing the full message history to that agent.

API Reference: tool | InjectedToolCallId | InjectedState | StateGraph | START | Command

from typing import Annotated
from langchain_core.tools import tool, InjectedToolCallId
from langgraph.prebuilt import InjectedState
from langgraph.graph import StateGraph, START, MessagesState
from langgraph.types import Command


def create_handoff_tool(*, agent_name: str, description: str | None = None):
    name = f"transfer_to_{agent_name}"
    description = description or f"Ask {agent_name} for help."

    @tool(name, description=description)
    def handoff_tool(
        state: Annotated[MessagesState, InjectedState],
        tool_call_id: Annotated[str, InjectedToolCallId],
    ) -> Command:
        tool_message = {
            "role": "tool",
            "content": f"Successfully transferred to {agent_name}",
            "name": name,
            "tool_call_id": tool_call_id,
        }
        return Command(
            goto=agent_name,  # (1)!
            update={**state, "messages": state["messages"] + [tool_message]},  # (2)!
            graph=Command.PARENT,  # (3)!
        )

    return handoff_tool


# Handoffs
assign_to_research_agent = create_handoff_tool(
    agent_name="research_agent",
    description="Assign task to a researcher agent.",
)

assign_to_math_agent = create_handoff_tool(
    agent_name="math_agent",
    description="Assign task to a math agent.",
)
  1. Name of the agent or node to hand off to.
  2. Take the agent's messages and add them to the parent's state as part of the handoff. The next agent will see the parent state.
  3. Indicate to LangGraph that we need to navigate to agent node in a parent multi-agent graph.

Create supervisor agent

Then, let's create the supervisor agent with the handoff tools we just defined. We will use the prebuilt create_react_agent:

supervisor_agent = create_react_agent(
    model="openai:gpt-4.1",
    tools=[assign_to_research_agent, assign_to_math_agent],
    prompt=(
        "You are a supervisor managing two agents:\n"
        "- a research agent. Assign research-related tasks to this agent\n"
        "- a math agent. Assign math-related tasks to this agent\n"
        "Assign work to one agent at a time, do not call agents in parallel.\n"
        "Do not do any work yourself."
    ),
    name="supervisor",
)

Create multi-agent graph

Putting this all together, let's create a graph for our overall multi-agent system. We will add the supervisor and the individual agents as subgraph nodes.

API Reference: END

from langgraph.graph import END

# Define the multi-agent supervisor graph
supervisor = (
    StateGraph(MessagesState)
    # NOTE: `destinations` is only needed for visualization and doesn't affect runtime behavior
    .add_node(supervisor_agent, destinations=("research_agent", "math_agent", END))
    .add_node(research_agent)
    .add_node(math_agent)
    .add_edge(START, "supervisor")
    # always return back to the supervisor
    .add_edge("research_agent", "supervisor")
    .add_edge("math_agent", "supervisor")
    .compile()
)

Notice that we've added explicit edges from worker agents back to the supervisor — this means that they are guaranteed to return control back to the supervisor. If you want the agents to respond directly to the user (i.e., turn the system into a router, you can remove these edges).

from IPython.display import display, Image

display(Image(supervisor.get_graph().draw_mermaid_png()))

With the multi-agent graph created, let's now run it!

for chunk in supervisor.stream(
    {
        "messages": [
            {
                "role": "user",
                "content": "find US and New York state GDP in 2024. what % of US GDP was New York state?",
            }
        ]
    },
):
    pretty_print_messages(chunk, last_message=True)

final_message_history = chunk["supervisor"]["messages"]

Update from node supervisor:


================================= Tool Message =================================
Name: transfer_to_research_agent

Successfully transferred to research_agent


Update from node research_agent:


================================== Ai Message ==================================
Name: research_agent

- US GDP in 2024 is projected to be about $28.18 trillion USD (Statista; CBO projection).
- New York State's nominal GDP for 2024 is estimated at approximately $2.16 trillion USD (various economic reports).
- New York State's share of US GDP in 2024 is roughly 7.7%.

Sources:
- https://www.statista.com/statistics/216985/forecast-of-us-gross-domestic-product/
- https://nyassembly.gov/Reports/WAM/2025economic_revenue/2025_report.pdf?v=1740533306


Update from node supervisor:


================================= Tool Message =================================
Name: transfer_to_math_agent

Successfully transferred to math_agent


Update from node math_agent:


================================== Ai Message ==================================
Name: math_agent

US GDP in 2024: $28.18 trillion
New York State GDP in 2024: $2.16 trillion
Percentage of US GDP from New York State: 7.67%


Update from node supervisor:


================================== Ai Message ==================================
Name: supervisor

Here are your results:

- 2024 US GDP (projected): $28.18 trillion USD
- 2024 New York State GDP (estimated): $2.16 trillion USD
- New York State's share of US GDP: approximately 7.7%

If you need the calculation steps or sources, let me know!
Let's examine the full resulting message history:

for message in final_message_history:
    message.pretty_print()

================================ Human Message =================================

find US and New York state GDP in 2024. what % of US GDP was New York state?
================================== Ai Message ==================================
Name: supervisor
Tool Calls:
  transfer_to_research_agent (call_KlGgvF5ahlAbjX8d2kHFjsC3)
 Call ID: call_KlGgvF5ahlAbjX8d2kHFjsC3
  Args:
================================= Tool Message =================================
Name: transfer_to_research_agent

Successfully transferred to research_agent
================================== Ai Message ==================================
Name: research_agent
Tool Calls:
  tavily_search (call_ZOaTVUA6DKrOjWQldLhtrsO2)
 Call ID: call_ZOaTVUA6DKrOjWQldLhtrsO2
  Args:
    query: US GDP 2024 estimate or actual
    search_depth: advanced
  tavily_search (call_QsRAasxW9K03lTlqjuhNLFbZ)
 Call ID: call_QsRAasxW9K03lTlqjuhNLFbZ
  Args:
    query: New York state GDP 2024 estimate or actual
    search_depth: advanced
================================= Tool Message =================================
Name: tavily_search

{"query": "US GDP 2024 estimate or actual", "follow_up_questions": null, "answer": null, "images": [], "results": [{"url": "https://www.advisorperspectives.com/dshort/updates/2025/05/29/gdp-gross-domestic-product-q1-2025-second-estimate", "title": "Q1 GDP Second Estimate: Real GDP at -0.2%, Higher Than Expected", "content": "> Real gross domestic product (GDP) decreased at an annual rate of 0.2 percent in the first quarter of 2025 (January, February, and March), according to the second estimate released by the U.S. Bureau of Economic Analysis. In the fourth quarter of 2024, real GDP increased 2.4 percent. The decrease in real GDP in the first quarter primarily reflected an increase in imports, which are a subtraction in the calculation of GDP, and a decrease in government spending. These movements were partly [...] by [Harry Mamaysky](https://www.advisorperspectives.com/search?author=Harry%20Mamaysky) of [QuantStreet Capital](https://www.advisorperspectives.com/firm/quantstreet-capital), 10/14/2024\n\n#### [The Worst of Allan Roth](https://www.advisorperspectives.com/articles/2024/10/21/worst-of-allan-roth/)\n\n by [Allan Roth](https://www.advisorperspectives.com/search?author=Allan%20Roth), 10/21/2024 [...] by [Juan Pablo Spinetto](https://www.advisorperspectives.com/search?author=Juan%20Pablo%20Spinetto) of [Bloomberg News](https://www.advisorperspectives.com/firm/bloomberg-news), 04/05/2025\n\n#### [Your Clients Are Clueless About Their Risk Tolerance](https://www.advisorperspectives.com/articles/2024/10/23/clients-clueless-about-risk-tolerance/)\n\n by [Dan Solin](https://www.advisorperspectives.com/search?author=Dan%20Solin), 10/23/2024", "score": 0.78650844, "raw_content": null}, {"url": "https://www.statista.com/statistics/216985/forecast-of-us-gross-domestic-product/", "title": "GDP forecast U.S. 2034 - Statista", "content": "[](https://www.statista.com/statistics/216985/forecast-of-us-gross-domestic-product/#statisticContainer) This graph shows a forecast of the gross domestic product of the United States of America for fiscal years 2024 to 2034. GDP refers to the market value of all final goods and services produced within a country in a given period. According to the CBO, the United States GDP will increase steadily over the next decade from 28.18 trillion U.S. dollars in 2023 to 41.65 trillion U.S. dollars in [...] US Congressional Budget Office. (February 7, 2024). Forecast of the gross domestic product of the United States from fiscal year 2024 to fiscal year 2034 (in billion U.S. dollars) [Graph]. In Statista. Retrieved May 20, 2025, from https://www.statista.com/statistics/216985/forecast-of-us-gross-domestic-product/ [...] US Congressional Budget Office. (2024). Forecast of the gross domestic product of the United States from fiscal year 2024 to fiscal year 2034 (in billion U.S. dollars). Statista. Statista Inc.. Accessed: May 20, 2025. https://www.statista.com/statistics/216985/forecast-of-us-gross-domestic-product/", "score": 0.7576693, "raw_content": null}, {"url": "https://www.bea.gov/data/gdp/gross-domestic-product", "title": "Gross Domestic Product | U.S. Bureau of Economic Analysis (BEA)", "content": "Real gross domestic product (GDP) decreased at an annual rate of 0.2 percent in the first quarter of 2025 (January, February, and March), according to the second estimate released by the U.S. Bureau of Economic Analysis. In the fourth quarter of 2024, real GDP increased 2.4 percent. The decrease in real GDP in the first quarter primarily reflected an increase in imports, which are a subtraction in the calculation of GDP, and a decrease in government spending. These movements were partly offset", "score": 0.75723875, "raw_content": null}], "response_time": 2.48}
================================= Tool Message =================================
Name: tavily_search

{"query": "New York state GDP 2024 estimate or actual", "follow_up_questions": null, "answer": null, "images": [], "results": [{"url": "https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/", "title": "Annual State of the City's Economy and Finances 2024", "content": "[[1]](https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/#_ftnref1) At that time, the Comptroller’s Office expected five-year cumulative real GDP growth, 2020 to 2024, of 8.7 percent while the mayor expected 9.5 percent.\n\n[[2]](https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/#_ftnref2) U.S. Bureau of Labor Statistics Local Area Unemployment Statistics (LAUS). [...] [[19]](https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/#_ftnref19) FY 2024 actuals include $742 million in transfers to the capital fund through Interfund Agreements, as detailed in Schedule G6 of the FY 2024 Annual Comprehensive Financial Report. [...] (constant 2019 dollars)**22,550 15,322 13,596 19,451 21,211 21,096\n**_% change_**(32.1%)(11.3%)43.1%9.0%(0.5%)\n\nSource: NY State Department of Taxation and Finance and Office of the New York City Comptroller", "score": 0.82795376, "raw_content": null}], "response_time": 2.76}
================================== Ai Message ==================================
Name: research_agent
Tool Calls:
  tavily_search (call_DxuGWv9Ii19fPys582KcSLOg)
 Call ID: call_DxuGWv9Ii19fPys582KcSLOg
  Args:
    query: New York state GDP 2024 (in dollars, not percentage growth or projections)
    search_depth: advanced
================================= Tool Message =================================
Name: tavily_search

{"query": "New York state GDP 2024 (in dollars, not percentage growth or projections)", "follow_up_questions": null, "answer": null, "images": [], "results": [{"url": "https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/", "title": "Annual State of the City's Economy and Finances 2024", "content": "(constant 2019 dollars)**22,550 15,322 13,596 19,451 21,211 21,096\n**_% change_**(32.1%)(11.3%)43.1%9.0%(0.5%)\n\nSource: NY State Department of Taxation and Finance and Office of the New York City Comptroller [...] | Retail Trade | 301,565 | $56,208 | 14.4 | (0.6) | (5.2) | 2.7 | 2.9 | 2.2 | 2.1 |\n| Leisure & Hospitality | 431,227 | $56,086 | 96.2 | 32.4 | 15.4 | 8.9 | 3.8 | 4.5 | 7.3 |\n| **Total: Low Wage Sectors** | **1,997,491** | **$62,185** | **184.6** | **102.2** | **91.6** | **62.7** | **32.0** | **26.8** | **29.3** |\n| **Total NYC Employment** | **4,485,695** | **$114,294** | **307.7** | **119.9** | **78.1** | **88.0** | **65.1** | **53.2** | **51.4** | [...] [[1]](https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/#_ftnref1) At that time, the Comptroller’s Office expected five-year cumulative real GDP growth, 2020 to 2024, of 8.7 percent while the mayor expected 9.5 percent.\n\n[[2]](https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/#_ftnref2) U.S. Bureau of Labor Statistics Local Area Unemployment Statistics (LAUS).", "score": 0.8098936, "raw_content": null}, {"url": "https://nyassembly.gov/Reports/WAM/2025economic_revenue/2025_report.pdf?v=1740533306", "title": "[PDF] New York State Economic and Revenue Report", "content": "Sources: Federal Reserve; NYS Assembly Ways and Means Committee staff. NYS ASSEMBLY| U.S. ECONOMIC FORECAST AT A GLANCE| 15 Actual Actual Actual Forecast Forecast 2022 2023 2024 2025 2026 Real GDP 2.5 2.9 2.8 2.4 2.1 Consumption 3.0 2.5 2.8 2.7 2.1 Investment 6.0 0.1 4.0 3.1 3.8 Exports 7.5 2.8 3.2 2.4 1.1 Imports 8.6 (1.2) 5.4 3.5 1.3 Government (1.1) 3.9 3.4 1.5 0.1 Federal (3.2) 2.9 2.5 1.7 0.2 State and Local 0.2 4.4 3.9 1.4 0.1 Personal Income 3.1 5.9 5.5 5.0 4.9 Wages & Salaries 7.8 5.4 [...] in 2024 on an annualized basis. National output, measured with inflation-adjusted Gross Domestic Product (or real GDP), continues to grow at solid rates, surpassing its pre-pandemic peak by 12.1 percent, as of the fourth quarter of 2024 (see Figure 2). However, the pace of average quarterly growth has decelerated from 3.2 percent in 2023 to 2.5 percent in 2024 on an annualized basis. 121.7 114.5 115.3 112.1 109.2 106.3 70 75 80 85 90 95 100 105 110 115 120 125 130 2019Q4 2020Q2 2020Q4 2021Q2 [...] three-month moving average of 2.5 million in December 2023 to 872,000 in December 2024. The ratio of job openings to unemployed persons, another key metric for assessing the balance between labor demand and supply, has also steadily declined in recent months. By December 2024, this ratio had dropped to 1.10, down from its peak of 2.03 in March 2022. 24 | U.S. ECONOMIC FORECAST ANALYSIS | NYS ASSEMBLY With diminishing supply shortages in the labor market, growth of labor and other incomes will", "score": 0.8051581, "raw_content": null}], "response_time": 2.86}
================================== Ai Message ==================================
Name: research_agent
Tool Calls:
  tavily_search (call_wjYTJR9EnmCqzKrkrONpxYO0)
 Call ID: call_wjYTJR9EnmCqzKrkrONpxYO0
  Args:
    query: New York State GDP (nominal) in US dollars for 2024 (actual or forecast)
    search_depth: advanced
================================= Tool Message =================================
Name: tavily_search

{"query": "New York State GDP (nominal) in US dollars for 2024 (actual or forecast)", "follow_up_questions": null, "answer": null, "images": [], "results": [{"url": "https://nyassembly.gov/Reports/WAM/2025economic_revenue/2025_report.pdf?v=1740533306", "title": "[PDF] New York State Economic and Revenue Report", "content": "Sources: Federal Reserve; NYS Assembly Ways and Means Committee staff. NYS ASSEMBLY| U.S. ECONOMIC FORECAST AT A GLANCE| 15 Actual Actual Actual Forecast Forecast 2022 2023 2024 2025 2026 Real GDP 2.5 2.9 2.8 2.4 2.1 Consumption 3.0 2.5 2.8 2.7 2.1 Investment 6.0 0.1 4.0 3.1 3.8 Exports 7.5 2.8 3.2 2.4 1.1 Imports 8.6 (1.2) 5.4 3.5 1.3 Government (1.1) 3.9 3.4 1.5 0.1 Federal (3.2) 2.9 2.5 1.7 0.2 State and Local 0.2 4.4 3.9 1.4 0.1 Personal Income 3.1 5.9 5.5 5.0 4.9 Wages & Salaries 7.8 5.4 [...] New York State Economic Outlook (Percent Change) Actual Estimate Forecast Forecast 2023-24 2024-25 2025-26 2026-27 Employment Percent Change 1.8 1.5 1.0 0.8 Level (Thousands) 9,441.6 9,589.7 9,694.3 9,773.6 Personal Income Percent Change 5.2 5.8 4.6 4.4 Level (Billions) 1,581.5 1,671.1 1,754.9 1,835.0 Total Wages Percent Change 4.2 6.7 4.4 4.0 Level (Billions) 864.0 915.9 964.3 1,005.1 Base Wages Percent Change 5.1 5.4 4.4 4.3 Level (Billions) 764.0 803.1 840.7 876.6 Variable Compensation [...] is 0.3 percentage point above the forecast of the Division of the Budget. The Committee’s forecast is 0.1 percentage point above S&P Global forecast and Moody’s Analytics’ projection. The forecast is 0.2 percentage point above the Blue Chip Consensus forecast. Actual Estimate Forecast Forecast 2023 2024 2025 2026 Ways and Means 2.9 2.8 2.4 2.1 Division of the Budget 2.9 2.8 2.1 2.0 Blue Chip Consensus 2.9 2.8 2.2 2.0 Moody's Analytics 2.9 2.8 2.3 1.6 S&P Global 2.9 2.8 2.3 2.0 Sources: NYS", "score": 0.846159, "raw_content": null}, {"url": "https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/", "title": "Annual State of the City's Economy and Finances 2024", "content": "(constant 2019 dollars)**22,550 15,322 13,596 19,451 21,211 21,096\n**_% change_**(32.1%)(11.3%)43.1%9.0%(0.5%)\n\nSource: NY State Department of Taxation and Finance and Office of the New York City Comptroller [...] [[1]](https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/#_ftnref1) At that time, the Comptroller’s Office expected five-year cumulative real GDP growth, 2020 to 2024, of 8.7 percent while the mayor expected 9.5 percent.\n\n[[2]](https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/#_ftnref2) U.S. Bureau of Labor Statistics Local Area Unemployment Statistics (LAUS). [...] | Retail Trade | 301,565 | $56,208 | 14.4 | (0.6) | (5.2) | 2.7 | 2.9 | 2.2 | 2.1 |\n| Leisure & Hospitality | 431,227 | $56,086 | 96.2 | 32.4 | 15.4 | 8.9 | 3.8 | 4.5 | 7.3 |\n| **Total: Low Wage Sectors** | **1,997,491** | **$62,185** | **184.6** | **102.2** | **91.6** | **62.7** | **32.0** | **26.8** | **29.3** |\n| **Total NYC Employment** | **4,485,695** | **$114,294** | **307.7** | **119.9** | **78.1** | **88.0** | **65.1** | **53.2** | **51.4** |", "score": 0.7992077, "raw_content": null}], "response_time": 2.65}
================================== Ai Message ==================================
Name: research_agent

- US GDP in 2024 is projected to be about $28.18 trillion USD (Statista; CBO projection).
- New York State's nominal GDP for 2024 is estimated at approximately $2.16 trillion USD (various economic reports).
- New York State's share of US GDP in 2024 is roughly 7.7%.

Sources:
- https://www.statista.com/statistics/216985/forecast-of-us-gross-domestic-product/
- https://nyassembly.gov/Reports/WAM/2025economic_revenue/2025_report.pdf?v=1740533306
================================== Ai Message ==================================
Name: supervisor
Tool Calls:
  transfer_to_math_agent (call_WEBMqUupSKqT5slb6ilX2VEO)
 Call ID: call_WEBMqUupSKqT5slb6ilX2VEO
  Args:
================================= Tool Message =================================
Name: transfer_to_math_agent

Successfully transferred to math_agent
================================== Ai Message ==================================
Name: math_agent
Tool Calls:
  divide (call_fsn6la6HTqfNl3sLp9v1WVoz)
 Call ID: call_fsn6la6HTqfNl3sLp9v1WVoz
  Args:
    a: 2.16
    b: 28.18
================================= Tool Message =================================
Name: divide

0.0766501064584812
================================== Ai Message ==================================
Name: math_agent

US GDP in 2024: $28.18 trillion
New York State GDP in 2024: $2.16 trillion
Percentage of US GDP from New York State: 7.67%
================================== Ai Message ==================================
Name: supervisor

Here are your results:

- 2024 US GDP (projected): $28.18 trillion USD
- 2024 New York State GDP (estimated): $2.16 trillion USD
- New York State's share of US GDP: approximately 7.7%

If you need the calculation steps or sources, let me know!

Important

You can see that the supervisor system appends all of the individual agent messages (i.e., their internal tool-calling loop) to the full message history. This means that on every supervisor turn, supervisor agent sees this full history. If you want more control over:

  • how inputs are passed to agents: you can use LangGraph Send() primitive to directly send data to the worker agents during the handoff. See the task delegation example below

  • how agent outputs are added: you can control how much of the agent's internal message history is added to the overall supervisor message history by wrapping the agent in a separate node function:

    def call_research_agent(state):
    # return agent's final response,
    # excluding inner monologue
    response = research_agent.invoke(state)
    return {"messages": response["messages"][-1]}

4. Create delegation tasks

So far the individual agents relied on interpreting full message history to determine their tasks. An alternative approach is to ask the supervisor to formulate a task explicitly. We can do so by adding a task_description parameter to the handoff_tool function.

API Reference: Send

from langgraph.types import Send


def create_task_description_handoff_tool(
    *, agent_name: str, description: str | None = None
):
    name = f"transfer_to_{agent_name}"
    description = description or f"Ask {agent_name} for help."

    @tool(name, description=description)
    def handoff_tool(
        # this is populated by the supervisor LLM
        task_description: Annotated[
            str,
            "Description of what the next agent should do, including all of the relevant context.",
        ],
        # these parameters are ignored by the LLM
        state: Annotated[MessagesState, InjectedState],
    ) -> Command:
        task_description_message = {"role": "user", "content": task_description}
        agent_input = {**state, "messages": [task_description_message]}
        return Command(
            goto=[Send(agent_name, agent_input)],
            graph=Command.PARENT,
        )

    return handoff_tool


assign_to_research_agent_with_description = create_task_description_handoff_tool(
    agent_name="research_agent",
    description="Assign task to a researcher agent.",
)

assign_to_math_agent_with_description = create_task_description_handoff_tool(
    agent_name="math_agent",
    description="Assign task to a math agent.",
)

supervisor_agent_with_description = create_react_agent(
    model="openai:gpt-4.1",
    tools=[
        assign_to_research_agent_with_description,
        assign_to_math_agent_with_description,
    ],
    prompt=(
        "You are a supervisor managing two agents:\n"
        "- a research agent. Assign research-related tasks to this assistant\n"
        "- a math agent. Assign math-related tasks to this assistant\n"
        "Assign work to one agent at a time, do not call agents in parallel.\n"
        "Do not do any work yourself."
    ),
    name="supervisor",
)

supervisor_with_description = (
    StateGraph(MessagesState)
    .add_node(
        supervisor_agent_with_description, destinations=("research_agent", "math_agent")
    )
    .add_node(research_agent)
    .add_node(math_agent)
    .add_edge(START, "supervisor")
    .add_edge("research_agent", "supervisor")
    .add_edge("math_agent", "supervisor")
    .compile()
)

Note

We're using Send() primitive in the handoff_tool. This means that instead of receiving the full supervisor graph state as input, each worker agent only sees the contents of the Send payload. In this example, we're sending the task description as a single "human" message.

Let's now running it with the same input query:

for chunk in supervisor_with_description.stream(
    {
        "messages": [
            {
                "role": "user",
                "content": "find US and New York state GDP in 2024. what % of US GDP was New York state?",
            }
        ]
    },
    subgraphs=True,
):
    pretty_print_messages(chunk, last_message=True)

Update from subgraph supervisor:


    Update from node agent:


    ================================== Ai Message ==================================
    Name: supervisor
    Tool Calls:
      transfer_to_research_agent (call_tk8q8py8qK6MQz6Kj6mijKua)
     Call ID: call_tk8q8py8qK6MQz6Kj6mijKua
      Args:
        task_description: Find the 2024 GDP (Gross Domestic Product) for both the United States and New York state, using the most up-to-date and reputable sources available. Provide both GDP values and cite the data sources.


Update from subgraph research_agent:


    Update from node agent:


    ================================== Ai Message ==================================
    Name: research_agent
    Tool Calls:
      tavily_search (call_KqvhSvOIhAvXNsT6BOwbPlRB)
     Call ID: call_KqvhSvOIhAvXNsT6BOwbPlRB
      Args:
        query: 2024 United States GDP value from a reputable source
        search_depth: advanced
      tavily_search (call_kbbAWBc9KwCWKHmM5v04H88t)
     Call ID: call_kbbAWBc9KwCWKHmM5v04H88t
      Args:
        query: 2024 New York state GDP value from a reputable source
        search_depth: advanced


Update from subgraph research_agent:


    Update from node tools:


    ================================= Tool Message =================================
    Name: tavily_search

    {"query": "2024 United States GDP value from a reputable source", "follow_up_questions": null, "answer": null, "images": [], "results": [{"url": "https://www.focus-economics.com/countries/united-states/", "title": "United States Economy Overview - Focus Economics", "content": "The United States' Macroeconomic Analysis:\n------------------------------------------\n\n**Nominal GDP of USD 29,185 billion in 2024.**\n\n**Nominal GDP of USD 29,179 billion in 2024.**\n\n**GDP per capita of USD 86,635 compared to the global average of USD 10,589.**\n\n**GDP per capita of USD 86,652 compared to the global average of USD 10,589.**\n\n**Average real GDP growth of 2.5% over the last decade.**\n\n**Average real GDP growth of 2.5% over the last decade.**\n\nShare of the region's population [...] |  | 2020 | 2021 | 2022 | 2023 | 2024 |\n| --- | --- | --- | --- | --- | --- |\n| [Population (million)](https://www.focus-economics.com/country-indicator/united-states/population/) | 331 | 332 | 334 | 337 | 340 |\n| [GDP (USD bn)](https://www.focus-economics.com/country-indicator/united-states/gdp/) | 21,354 | 23,681 | 26,007 | 27,721 | 29,185 |", "score": 0.73981786, "raw_content": null}, {"url": "https://tradingeconomics.com/united-states/gdp", "title": "United States GDP - Trading Economics", "content": "| Related | Last | Previous | Unit | Reference |\n| --- | --- | --- | --- | --- |\n| [Full Year GDP Growth](/united-states/full-year-gdp-growth) | 2.80 | 2.90 | percent | Dec 2024 |\n| [GDP](/united-states/gdp) | 27720.71 | 26006.89 | USD Billion | Dec 2023 |\n| [GDP Annual Growth Rate](/united-states/gdp-growth-annual) | 2.10 | 2.50 | percent | Mar 2025 |\n| [GDP Constant Prices](/united-states/gdp-constant-prices) | 23528.00 | 23542.30 | USD Billion | Mar 2025 |", "score": 0.65359193, "raw_content": null}, {"url": "https://fred.stlouisfed.org/series/GDP", "title": "Gross Domestic Product (GDP) | FRED | St. Louis Fed", "content": "Q1 2025: 29,976.638 |\nBillions of Dollars, Seasonally Adjusted Annual Rate |\nQuarterly\n\nUpdated:\nMay 29, 2025\n7:56 AM CDT\n\n[Next Release Date:\nJun 26, 2025](/releases/calendar?rid=53&y=2025)\n\nObservations\n\n|  |  |  |\n| --- | --- | --- |\n| Q1 2025: | 29,976.638 |  |\n| Q4 2024: | 29,723.864 |  |\n| Q3 2024: | 29,374.914 |  |\n| Q2 2024: | 29,016.714 |  |\n| Q1 2024: | 28,624.069 |  |\n| [View All](/data/GDP.txt) | |\n\nUnits:\n\nFrequency:", "score": 0.6152965, "raw_content": null}], "response_time": 2.53}


Update from subgraph research_agent:


    Update from node tools:


    ================================= Tool Message =================================
    Name: tavily_search

    {"query": "2024 New York state GDP value from a reputable source", "follow_up_questions": null, "answer": null, "images": [], "results": [{"url": "https://www.ibisworld.com/united-states/economic-profiles/new-york/", "title": "New York Economic Trends, Stats & Rankings | IBISWorld", "content": "#### What is New York's Gross Domestic Product (GDP)?\n\nIn 2024, New York's GDP reached $1.8tn, representing an increase of 1.3% from 2023. New York's GDP has grown at an annualized rate of 2.9% over the five years to 2024. Moreover, New York's trailing five-year GDP growth ranks it 37th out of all 50 US states. [...] In 2024, the state of New York has a population of 19,482,372, having grown an annualized 0.0% over the five years to 2024, which ranks it 44th out of all 50 US states by growth rate. New York's gross state product (GSP) in 2024 reached $1.8tn, with growth of 1.3% over the 5 years to 2024. Businesses in New York employed a total of 11,671,845 people in 2024, with average annual employment growth over the past five years of 0.0%. The top three sectors by total employment are Finance and [...] The Finance and Insurance, Real Estate and Rental and Leasing and Information sectors contributed the most to New York's GDP in 2024, representing a combined 46.3% of state GDP.\n\nGDP trends by sector are an important indicator of which sectors are contributing the most value-add to the state's economy, in addition to how the state economy is evolving over time.\n\nSector\n\nGDP\n\nGrowth 2024 (%)\n\nAnnualized Growth 2019-24", "score": 0.8051581, "raw_content": null}, {"url": "https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/", "title": "Annual State of the City's Economy and Finances 2024", "content": "(constant 2019 dollars)**22,550 15,322 13,596 19,451 21,211 21,096\n**_% change_**(32.1%)(11.3%)43.1%9.0%(0.5%)\n\nSource: NY State Department of Taxation and Finance and Office of the New York City Comptroller [...] [[1]](https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/#_ftnref1) At that time, the Comptroller’s Office expected five-year cumulative real GDP growth, 2020 to 2024, of 8.7 percent while the mayor expected 9.5 percent.\n\n[[2]](https://comptroller.nyc.gov/reports/annual-state-of-the-citys-economy-and-finances-2024/#_ftnref2) U.S. Bureau of Labor Statistics Local Area Unemployment Statistics (LAUS). [...] **($ in millions)****FY 2025****FY 2026****FY 2027****FY 2028****Total****Change from June 2024 (FY2025-FY2028)****Source as Share of Total**\n**General Obligation Bonds**$6,900$6,230$6,920$7,110$27,160$1,960 42.8%\n**TFA FTS Bonds**6,900 6,230 6,920 7,110 27,160 2,460 42.8%\n**NYC Water Finance Authority**1,726 2,474 2,452 2,505 9,157 435 14.4%\n**Total****$15,526****$14,934****$16,292****$16,725****$63,477****$4,855****100.0%**", "score": 0.74541736, "raw_content": null}], "response_time": 3.45}


Update from subgraph research_agent:


    Update from node agent:


    ================================== Ai Message ==================================
    Name: research_agent

    - United States 2024 GDP: $29.2 trillion (USD)  
      Source: [Focus Economics](https://www.focus-economics.com/countries/united-states/)

    - New York State 2024 GDP: $1.8 trillion (USD)  
      Source: [IBISWorld](https://www.ibisworld.com/united-states/economic-profiles/new-york/)


Update from subgraph supervisor:


    Update from node agent:


    ================================== Ai Message ==================================
    Name: supervisor
    Tool Calls:
      transfer_to_math_agent (call_EqT01HDOQDd5Timk89cccdXP)
     Call ID: call_EqT01HDOQDd5Timk89cccdXP
      Args:
        task_description: Calculate what percentage of the US GDP ($29.2 trillion) was New York State's GDP ($1.8 trillion) in 2024. Show your working and round the final answer to two decimal points.


Update from subgraph math_agent:


    Update from node agent:


    ================================== Ai Message ==================================
    Name: math_agent
    Tool Calls:
      divide (call_OpdUlYEFqk4RZ2rF46M9eTrS)
     Call ID: call_OpdUlYEFqk4RZ2rF46M9eTrS
      Args:
        a: 1.8
        b: 29.2


Update from subgraph math_agent:


    Update from node tools:


    ================================= Tool Message =================================
    Name: divide

    0.06164383561643836


Update from subgraph math_agent:


    Update from node agent:


    ================================== Ai Message ==================================
    Name: math_agent
    Tool Calls:
      multiply (call_vdKJTLtIzmG6JbPcGQn93MR6)
     Call ID: call_vdKJTLtIzmG6JbPcGQn93MR6
      Args:
        a: 0.06164383561643836
        b: 100


Update from subgraph math_agent:


    Update from node tools:


    ================================= Tool Message =================================
    Name: multiply

    6.164383561643836


Update from subgraph math_agent:


    Update from node agent:


    ================================== Ai Message ==================================
    Name: math_agent

    New York State's GDP was approximately 6.16% of the US GDP in 2024.


Update from subgraph supervisor:


    Update from node agent:


    ================================== Ai Message ==================================
    Name: supervisor

    New York State’s GDP was approximately 6.16% of the US GDP in 2024.

    **Working:**
    - Percentage = (NY GDP / US GDP) × 100
    - = ($1.8 trillion / $29.2 trillion) × 100
    - = 0.06164 × 100
    - = 6.16% (rounded to two decimal points)