GitHub releases Copilot Code Review Max, using multiple AI models to collaborate on code review
At GitHub Universe 2026, GitHub released a new code review feature, Copilot Code Review Max, adding a Max tier on top of the existing Lite and Balanced tiers. The feature internally runs multiple independent review agents driven by AI models, with an aggregator agent coordinating disagreements and rechecking accuracy, in order to catch issues that a single model tends to miss. GitHub says it has the highest F1 score on ReviewBench for detecting high-risk code issues, and it is currently available as a public preview.
Why read this
AI score 54
The original article explains how the Max tier uses multiple models to each review independently and then aggregate the results, so readers can judge the difference between multi-agent review and single-model review.
Topics
Body · AI translation
Google Ad Server settings
Simple Analytics Placeholder event function
×
End of Header
End of superbanner /3002452/Pbk_Rect1_300x300
/3002452/Pbk_Rect2_300x250
GitHub announces "Copilot Code Review Max" for more advanced code review. GitHub Universe 2026, November 4, 2026
At "GitHub Universe 2026," its annual event held over two days, October 28 and 29, in San Francisco, USA, GitHub announced a new feature for more advanced code review called "Copilot Code Review Max."
GitHub Copilot has long offered a code review feature called "Copilot Code Review," which performs code reviews such as detecting bugs and provides the results to developers.
However, code generation and pull requests utilizing AI agents have increased dramatically, and code review has become increasingly important for maintaining software quality.
The newly announced "Copilot Code Review Max" provides more advanced code review capabilities.
"Copilot Code Review" has until now offered two effort levels, "Lite" and "Balanced." Copilot Code Review Max is realized through the newly added effort level "Max."
It is explained that inside Copilot Code Review Max, multiple independent review agents driven by multiple AI models are running. By effectively combining the strengths and blind spots of each AI model, it can find issues that a single AI model tends to overlook.
Then an aggregation agent coordinates the outputs of the multiple review agents, resolving discrepancies and re-verifying accuracy, before reporting the results as the review outcome.
According to GitHub's announcement, "Copilot Code Review Max" recorded the highest "F1 score" in detecting high-severity issues in code on ReviewBench.
Copilot Code Review Max is currently available as a public preview.
Related articles on GitHub Universe 2026
GitHub officially releases "Copilot Fusion." High performance and low cost by selecting the optimal AI model for the task. GitHub Universe 2026
GitHub announces "Copilot Code Review Max" for more advanced code review. GitHub Universe 2026
GitHub to achieve 180x throughput performance improvement over conventional levels, early next year. Adapting to the AI agent era. GitHub Universe 2026
Read together
Software testing/quality Machine learning/AI Development tools GitHub Microsoft
≫Next article: GitHub to achieve 180x throughput performance improvement over conventional levels, early next year. Adapting to the AI agent era. GitHub Universe 2026
≪Previous article: GitHub officially releases "Copilot Fusion." High performance and low cost by selecting the optimal AI model for the task. GitHub Universe 2026
After working as an editor at an IT magazine and a publisher of an online media outlet, became independent. Started Publickey in 2009.
(Detailed profile)
Would you like to check the latest news from Publickey?
GitHub to achieve 180x throughput performance improvement over conventional levels, early next year. Adapting to the AI agent era. GitHub Universe 2026
GitHub announces "Copilot Code Review Max" for more advanced code review. GitHub Universe 2026
GitHub officially releases "Copilot Fusion." High performance and low cost by selecting the optimal AI model for the task. GitHub Universe 2026
Oracle announces "Oracle App Composer," which lets employees automatically create business apps with AI and share them on Oracle Cloud. Oracle AI World 2026
Oracle Cloud announces adoption of Google TPU, to begin offering in 2027. Oracle AI World 2026
JavaScript runtime "Bun" offers a Prettier-compatible formatter more than 300 times faster. Prettier configuration files can be used as-is
AWS and Google Cloud open-source PyTorch versions for AWS Trainium and Google Cloud TPU. Taking on the challenge of migrating away from NVIDIA
"DuckDB 2.0 LTS" officially released. Client/server functionality via the Quack protocol and speedups through asynchronous processing, etc.
Cloudflare announces "tsrs," a port of TypeScript to Rust. Up to 8x faster with up to 70% less memory than TypeScript 7. Plans to support all TypeScript features including LSP in the future
Managed service offering for "Cloudflare OS." Strengthened integration with GitHub and Gmail, etc.
Our efforts to ensure readers can read articles with peace of mind
Simple Analytics 100% privacy-first analytics
- script for simple analytics events --
Global site tag (gtag.js) - Google Analytics