Deep Research Max: Enhanced Autonomous Research Agents with Gemini 3.1 Pro
Key Points
- Deep Research Max delivers expert-grade analysis with extended test-time compute for comprehensive research
- MCP support enables secure integration of proprietary and specialized professional data streams
- Native chart and infographic generation transforms complex data into presentation-ready visualizations
Summary
Google DeepMind has released two new autonomous research agents—Deep Research and Deep Research Max—built on Gemini 3.1 Pro. These agents represent a significant advancement in long-horizon research workflows, combining web search with proprietary data sources to deliver professional-grade, fully cited analyses.
Key Points
- Two Agent Variants: Deep Research optimized for speed and interactive surfaces; Deep Research Max designed for comprehensive, asynchronous workflows with extended test-time compute
- MCP Integration: Seamlessly connect custom data and specialized professional data streams (financial, market data) via Model Context Protocol for secure, gated data access
- Native Visualizations: Agents now generate high-quality charts and infographics inline with HTML or Nano Banana, transforming complex data into presentation-ready outputs
- Enhanced Data Access: Support for web search, remote MCPs, file uploads, connected file stores, PDFs, CSVs, images, audio and video as research inputs
- Collaborative Planning: Review and refine research plans before execution for granular control over investigation scope
- Real-time Streaming: Track intermediate reasoning steps with live thought summaries and receive outputs as generated
- Enterprise Partnerships: Active collaboration with FactSet, S&P Global, and PitchBook on MCP server designs for financial data integration
- Availability: Public preview via paid tiers in Gemini API; coming soon to Google Cloud startups and enterprises