Article complete

Microsoft Adds Critique Multi-Model AI to Copilot Researcher

The system uses models from providers, including Anthropic and OpenAI.

A stylized illustration of a man with glasses, featuring cloud and data graphics in a colorful design.

Key takeaways

  • Microsoft Copilot's Researcher gains multi-model AI for improved accuracy and structure.
  • Critique mode uses separate AI models for drafting and refining research outputs.
  • Critique significantly improved research accuracy, completeness, and objectivity on benchmarks.
  • Council mode compares research from multiple AI models, highlighting agreements and differences.

Takeaways drafted with AI from the article text.

Available through Microsoft’s Frontier program, the update uses separate AI models for generation and evaluation. Microsoft said this approach “raises the bar for accuracy, depth, and confidence” in research outputs.

Critique, the default mode, splits research into two stages. One model generates a draft by planning and retrieving information, while another reviews and refines it. 

“By giving evaluation as much emphasis as generation, this architecture creates a feedback loop that delivers higher-quality results,” the company said.

The system uses models from providers including Anthropic and OpenAI. The reviewer model applies rubric-based checks focused on source reliability, completeness, and evidence grounding.

Microsoft said performance improved on the DRACO benchmark, which measures research accuracy, completeness, and objectivity across 100 tasks. Researcher with Critique recorded a 7-point increase in aggregated scores, a 13.88% gain over Perplexity’s system using Claude Opus 4.6.

The company reported gains across evaluation metrics, including breadth and depth of analysis, presentation quality, and factual accuracy. “Critique pushes Researcher to identify missing analytical angles, close coverage gaps, and strengthen claims,” Microsoft said.

On the other hand, Council offers a parallel approach. It runs models from Anthropic and OpenAI side by side, generating separate reports. A judge model then summarises areas of agreement and differences.



Published

Spotted an error? Tell our editors. Read our editorial standards and corrections.

More in this story

AI Research · 3 stories
  1. You are here: Microsoft Adds Critique Multi-Model AI to Copilot Researcher
  2. OpenAI Spent $34 Billion in 2025: Report
  3. Microsoft Outage: Fix Fails to Restore Outlook, Teams, Copilot Across 74 Countries
About the author

Tech Journalist

Siddharth is a media graduate who loves to explore tech through journalism and putting forward ideas worth pondering about in the era of artificial intelligence.

All stories
Belamy · Daily

The day’s AI news, before your first meeting.