Along with the new Gemini 2.0 Flash model and Trillium TPU GA, Google today announced a new feature called Deep Research in Gemini. Deep Research is an AI research assistant that can dig into complex subjects and create reports with relevant citations.
We’re also introducing a new agentic feature called Deep Research in Gemini Advanced, a research assistant that can dig into complex topics and create reports for you with links to the relevant sources. pic.twitter.com/imYd4tktEG
— Sundar Pichai (@sundarpichai) December 11, 2024
Doing research online is not an easy task. It will consume several hours, opening a sea of browser tabs, clipping information from everywhere, organizing it together, and more. Gemini Deep Research can now perform online research under the user"s supervision.
Once users provide a research question, Deep Research creates a multi-step research plan. Users can either revise or approve the research plan. Once approved, it begins deeply analyzing relevant information from across the web.
Deep Research takes several minutes to complete a task. Over this period, it continuously refines its analysis based on the content it learned from browsing the web. It repeats this process multiple times and finally gives a comprehensive report of the key findings to the user.
Deep Research organizes the report with citations, and users can also export the report to Google Docs for further editing. Users can also add follow-up questions to further refine the report.
Dave Citron, Senior Director, Product Management, Gemini app, wrote the following regarding the Deep Research feature launch:
"Earlier this year, we shared our vision of building more agentic capabilities into our products; Deep Research is the first feature in Gemini to bring that vision to life. We’ve built a new agentic system that uses Google"s expertise of finding relevant information on the web to direct Gemini"s browsing and research."
Google is now rolling out Deep Research to Gemini Advanced users with English language on desktop and mobile web. Google will also bring it to the mobile app in early 2025. To use this new feature, users can switch to “Gemini 1.5 Pro with Deep Research” from the model drop-down.
This new Gemini Deep Research feature is a significant step towards making AI more useful for academic and professional research. It also indicates that Gemini is getting even better at completing complex tasks that will help users save a lot of time.