Deep Research is only available to Gemini Advanced users
The feature is available in 45 languages
The Deep Research capability can be selected from Gemini’s model switcher
Deep Research can run several new web searches based on its learnings
Photo Credit: Google
Google is expanding the Deep Research tool to the Gemini Android app. The first artificial intelligence (AI) agent for Gemini was so far available only on the web version of the platform. The Mountain View-based tech giant released the tool in December 2024, and described it as a research assistant that can create multi-step research plans, run web searches, and prepare a detailed report on complex topics. Notably, the agentic function is currently only available to the paid subscribers of Gemini.
Deep Research AI Agent Being Added to Gemini App for Android
The official handle of Gemini on X (formerly known as Twitter) announced the expansion of the AI agent in a post. The post highlighted that it is currently being rolled out, so it might take a couple of weeks before users globally begin to see the feature on the Android app. Once added, Deep Research can be accessed in the Gemini Advanced drop-down menu.
At the time of launch, the company said that the feature would be available in 45 languages including Arabic, Bengali, English, French, Japanese, Russian, Tamil, and Vietnamese. Deep Research is powered by the recently released Gemini 1.5 Pro and can act as a research assistant for the user.
Once a prompt has been added about a complex topic, the AI agent creates a multi-step research plan. The user can check and edit the plan to add, remove, or change items in the list. After that, it looks through relevant research papers, articles and other trusted sources for relevant information. It also looks into recent developments in the topic, current trends, as well as future outlook.
It can also run several new web searches if the AI agent feels it needs to gain context from additional topics. Once the agent has enough information, it generates a detailed report about the topic. The user can intervene and take control at any point in the entire process.
Based on its learnings, the agent can also run several new web searches to gain a deeper understanding of the topic. Once the agent has enough information, it generates a detailed report. The user has the option to intervene during any step and either edit the research plan or add a follow-up prompt to modify the output.
Google Pixel 9a Reportedly Runs Smaller Gemini Nano LLM, Misses Out on AI Features Due to RAM Constraints21 March 2025
Search
![Gadgets 360 With Technical Guruji: Ask TG [ March 22, 2025]](https://c.ndtvimg.com/2024-12/5s52e4k_-ask-tg_640x480_14_December_24.jpg?downsize=180:*)
