Google is developing a multi-agent system in Gemini for Enterprise that generates and evaluates ideas through a tournament-style process. Users can receive up to 100 ranked ideas based on specified topics and criteria. The system also includes specialized agents like "Co-scientist," aimed at aiding research and scientific inquiries.

The article discusses the development of a multi-agent research system by Anthropic, which aims to enhance collaboration and interaction among AI agents. This system is designed to facilitate more robust research and experimentation in the field of artificial intelligence, focusing on achieving advanced decision-making capabilities.