Google DeepMind releases Gemini multi-agent research system
Google DeepMind 发布 Gemini 多智能体科研系统
Google DeepMind introduced Co-Scientist, a Gemini-based multi-agent system that generates, debates, and evolves scientific hypotheses; the post does not disclose the Gemini version, benchmark results, access model, or release timeline.
Why it matters: Co-Scientist splits hypothesis generation, debate and iteration across multiple Gemini agents, showing how multi-agent setups can work in research.