Gemini Deep Research agent

The Gemini Deep Research agent autonomously plans, executes, and synthesizes multi-step research tasks. Powered by Gemini, it navigates complex information landscapes to produce detailed, cited reports. New capabilities allow you to collaboratively plan with the agent, connect to external tools using MCP servers, include visualizations (like charts and graphs), and provide documents directly as input.

Research tasks involve iterative searching and reading and can take several minutes to complete. You must use background execution (set background=true) to run the agent asynchronously and poll for results or stream updates. See Handling long-running tasks for more details.

The following example shows how to start a research task in the background and poll for results.

Python

import time
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    input="Research the history of Google TPUs.",
    agent="deep-research-preview-04-2026",
    background=True,
)

print(f"Research started: {interaction.id}")

while True:
    interaction = client.interactions.get(interaction.id)
    if interaction.status == "completed":
        print(interaction.steps[-1].content[0].text)
        break
    elif interaction.status == "failed":
        print(f"Research failed: {interaction.error}")
        break
    time.sleep(10)

JavaScript

import { GoogleGenAI } from '@google/genai';

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    input: 'Research the history of Google TPUs.',
    agent: 'deep-research-preview-04-2026',
    background: true
});

console.log(`Research started: ${interaction.id}`);

while (true) {
    const result = await client.interactions.get(interaction.id);
    if (result.status === 'completed') {
        console.log(result.steps.at(-1).content[0].text);
        break;
    } else if (result.status === 'failed') {
        console.log(`Research failed: ${result.error}`);
        break;
    }
    await new Promise(resolve => setTimeout(resolve, 10000));
}

REST

# 1. Start the research task
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "input": "Research the history of Google TPUs.",
    "agent": "deep-research-preview-04-2026",
    "background": true
}'

# 2. Poll for results (Replace INTERACTION_ID)
# curl -X GET "https://generativelanguage.googleapis.com/v1beta/interactions/INTERACTION_ID" \
# -H "x-goog-api-key: $GEMINI_API_KEY"

Supported versions

The Deep Research agent comes in two versions:

  • Deep Research (deep-research-preview-04-2026): Designed for speed and efficiency, ideal to be streamed back to a client UI.
  • Deep Research Max (deep-research-max-preview-04-2026): Maximum comprehensiveness for automated context gathering and synthesis.

Collaborative planning

Collaborative planning gives you control over the research direction before the agent starts its work by letting you review and refine the research plan before execution. When enabled, the agent returns a proposed research plan instead of executing immediately. You can then review, modify, or approve the plan through multi-turn interactions.

Step 1: Request a plan

Set collaborative_planning=True in the first interaction. The agent returns a research plan instead of a full report.

Python

from google import genai

client = genai.Client()

# First interaction: request a research plan
plan_interaction = client.interactions.create(
    agent="deep-research-preview-04-2026",
    input="Do some research on Google TPUs.",
    agent_config={
        "type": "deep-research",
        "thinking_summaries": "auto",
        "collaborative_planning": True,
    },
    background=True,
)

# Wait for and retrieve the plan
while (result := client.interactions.get(id=plan_interaction.id)).status != "completed":
    time.sleep(5)
print(result.steps[-1].content[0].text)

JavaScript

const planInteraction = await client.interactions.create({
    agent: 'deep-research-preview-04-2026',
    input: 'Do some research on Google TPUs.',
    agent_config: {
        type: 'deep-research',
        thinking_summaries: 'auto',
        collaborative_planning: true
    },
    background: true
});

let result;
while ((result = await client.interactions.get(planInteraction.id)).status !== 'completed') {
    await new Promise(r => setTimeout(r, 5000));
}
console.log(result.steps.at(-1).content[0].text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "agent": "deep-research-preview-04-2026",
    "input": "Do some research on Google TPUs.",
    "agent_config": {
        "type": "deep-research",
        "thinking_summaries": "auto",
        "collaborative_planning": true
    },
    "background": true
}'

Step 2: Refine the plan (optional)

Use previous_interaction_id to continue the conversation and iterate on the plan. Keep collaborative_planning=True to stay in planning mode.

Python

# Second interaction: refine the plan
refined_plan = client.interactions.create(
    agent="deep-research-preview-04-2026",
    input="Focus more on the differences between Google TPUs and competitor hardware, and less on the history.",
    agent_config={
        "type": "deep-research",
        "thinking_summaries": "auto",
        "collaborative_planning": True,
    },
    previous_interaction_id=plan_interaction.id,
    background=True,
)

while (result := client.interactions.get(id=refined_plan.id)).status != "completed":
    time.sleep(5)
print(result.steps[-1].content[0].text)

JavaScript

const refinedPlan = await client.interactions.create({
    agent: 'deep-research-preview-04-2026',
    input: 'Focus more on the differences between Google TPUs and competitor hardware, and less on the history.',
    agent_config: {
        type: 'deep-research',
        thinking_summaries: 'auto',
        collaborative_planning: true
    },
    previous_interaction_id: planInteraction.id,
    background: true
});

let result;
while ((result = await client.interactions.get(refinedPlan.id)).status !== 'completed') {
    await new Promise(r => setTimeout(r, 5000));
}
console.log(result.steps.at(-1).content[0].text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "agent": "deep-research-preview-04-2026",
    "input": "Focus more on the differences between Google TPUs and competitor hardware, and less on the history.",
    "agent_config": {
        "type": "deep-research",
        "thinking_summaries": "auto",
        "collaborative_planning": true
    },
    "previous_interaction_id": "PREVIOUS_INTERACTION_ID",
    "background": true
}'

Step 3: Approve and execute

Set collaborative_planning=False (or omit it) to approve the plan and start the research.

Python

# Third interaction: approve the plan and kick off research
final_report = client.interactions.create(
    agent="deep-research-preview-04-2026",
    input="Plan looks good!",
    agent_config={
        "type": "deep-research",
        "thinking_summaries": "auto",
        "collaborative_planning": False,
    },
    previous_interaction_id=refined_plan.id,
    background=True,
)

while (result := client.interactions.get(id=final_report.id)).status != "completed":
    time.sleep(5)
print(result.steps[-1].content[0].text)

JavaScript

const finalReport = await client.interactions.create({
    agent: 'deep-research-preview-04-2026',
    input: 'Plan looks good!',
    agent_config: {
        type: 'deep-research',
        thinking_summaries: 'auto',
        collaborative_planning: false
    },
    previous_interaction_id: refinedPlan.id,
    background: true
});

let result;
while ((result = await client.interactions.get(finalReport.id)).status !== 'completed') {
    await new Promise(r => setTimeout(r, 5000));
}
console.log(result.steps.at(-1).content[0].text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "agent": "deep-research-preview-04-2026",
    "input": "Plan looks good!",
    "agent_config": {
        "type": "deep-research",
        "thinking_summaries": "auto",
        "collaborative_planning": false
    },
    "previous_interaction_id": "PREVIOUS_INTERACTION_ID",
    "background": true
}'

Visualization

When visualization is set to "auto", the agent can generate charts, graphs, and other visual elements to support its research findings. Generated images are included in the response steps and streamed as image deltas. For best results, explicitly ask for visuals in your query — for example, "Include charts showing trends over time" or "Generate graphics comparing market share." Setting visualization to "auto" enables the capability, but the agent generates visuals only when the prompt requests them.

Python

import base64
import time

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="deep-research-preview-04-2026",
    input="Analyze global semiconductor market trends. Include graphics showing market share changes.",
    agent_config={
        "type": "deep-research",
        "visualization": "auto",
    },
    background=True,
)

print(f"Research started: {interaction.id}")

while (result := client.interactions.get(id=interaction.id)).status != "completed":
    time.sleep(5)

for step in result.steps:
    if step.type == "model_output":
        for content_item in step.content:
            if content_item.type == "text":
                print(content_item.text)
            elif content_item.type == "image" and content_item.data:
                image_bytes = base64.b64decode(content_item.data)
                print(f"Received image: {len(image_bytes)} bytes")

JavaScript

import { GoogleGenAI } from '@google/genai';

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: 'deep-research-preview-04-2026',
    input: 'Analyze global semiconductor market trends. Include graphics showing market share changes.',
    agent_config: {