Google Releases Gemini Deep Research Agent
Google today announced a more powerful Gemini Deep Research agent, available to developers in preview and coming soon to consumer apps. The company also launched an Interactions API to unify model and agent access; the agent, powered by Gemini 3 Pro, is optimized for long-running context gathering, reduced hallucinations, improved web search, and posts higher benchmark scores (HLE 46.4% vs 43.2%, DeepSearchQA 66.1% vs 56.6%, BrowseComp 59.2% vs 49.4%).
Key Points
- 1Announces Gemini Deep Research agent using Gemini 3 Pro for advanced autonomous web research and synthesis
- 2Introduces Interactions API to unify model and agent access, reflecting advanced 'thinking' and tool use
- 3Enables developers to preview agent in Google AI Studio and integrate autonomous research into applications
Scoring Rationale
Official Google release with broad developer applicability and measurable benchmark gains, limited only by preview availability and consumer rollout timeline.
Sources
Public references used for this report.
Practice with real Ad Tech data
90 SQL & Python problems · 15 industry datasets
250 free problems · No credit card
See all Ad Tech problems