惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Vercel News
Vercel News
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Apple Machine Learning Research
Apple Machine Learning Research
T
Tailwind CSS Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
人人都是产品经理
人人都是产品经理
V
V2EX
量子位
Last Week in AI
Last Week in AI
Jina AI
Jina AI
博客园 - 【当耐特】
爱范儿
爱范儿
宝玉的分享
宝玉的分享
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Hugging Face - Blog
Hugging Face - Blog
博客园 - 三生石上(FineUI控件)
有赞技术团队
有赞技术团队
小众软件
小众软件
IT之家
IT之家
博客园_首页
博客园 - 聂微东
S
SegmentFault 最新的问题
阮一峰的网络日志
阮一峰的网络日志
博客园 - 叶小钗

The Official Google Blog

5 helpful tools from Google to keep your accounts safe This Teacher Appreciation Week, we’re celebrating educators who made a difference in our lives. Find out how AlphaEvolve has gone from research to solving real-life problems. Here’s how we're celebrating Asian American, Native Hawaiian and Pacific Islander Heritage Month 5 gardening tips you can try right in Search Google Flow Music and Believe bring next-gen tools to artists 5 new ways to explore the web with generative AI in Search AI is reshaping ad creative. Here’s how brands can get it right. Gemini API File Search is now multimodal: build efficient, verifiable RAG Approximate location sharing gives you more control over your location data in Chrome. Accelerating Gemma 4: faster inference with multi-token prediction drafters Here’s what’s new with Google Home. Celebrating educators’ creativity this Teacher Appreciation Week Turn your data into decisions: 3 things your business needs for growth in the AI era Here’s how we’re helping Belgium's farmers save water with AI. Putting educators at the center of AI learning The latest AI news we announced in April 2026 Here's how Google AI is powering small business growth Reduce friction and latency for long-running jobs with Webhooks in Gemini API Celebrating America’s 250th on Google Arts & Culture Supporting startups that are shaping the future of energy Your car with Google built-in is about to get smarter, thanks to Gemini Preferred Sources is now available in all languages. Adapt your Shopping campaigns to modern Search with AI Max. Meet travelers in the moments that matter with Search Campaigns for Travel. AI Max Turns 1 with new ways to steer performance and expansion to more advertisers How we’re protecting energy affordability in Oklahoma Alphabet is one of TIME’s 100 most influential companies of 2026. Q1 2026 earnings call: Remarks from our CEO A new way to create a digital wardrobe from your Google Photos
4 ways researchers are collaborating with Co-Scientist to...
Joel Meares · 2026-06-10 · via The Official Google Blog

Learn more about Co-Scientist and the impact it’s already making.

General summary

Researchers are now using Co-Scientist, an artificial intelligence system designed to help solve complex problems in the life sciences. The tool uses specialized agents to generate, debate, and refine new hypotheses, acting as a virtual partner for scientific discovery. You can explore how this technology accelerates research by visiting the Google DeepMind blog or testing the new experimental tool.

Summaries were generated by Google AI. Generative AI is experimental.

Your browser does not support the audio element.

Listen to article

This content is generated by Google AI. Generative AI is experimental

[[duration]] minutes

We recently published our latest research on Co-Scientist, a collaborative AI designed for structured scientific thinking to help researchers develop new hypotheses in life sciences and beyond.

The system is made up of a coalition of specialized agents that work together in three distinct phases. First, Co-Scientist generates ideas through agents that propose hypotheses and explore a wide variety of research avenues. Next, it debates ideas, with one agent that acts as a virtual peer reviewer before another pits vetted ideas against each other in an “idea tournament.” Finally, it evolves ideas, with agents that refine, combine and improve the best hypotheses, as well as agents that synthesize the research for a human scientist. A supervisor agent ties the system together, breaking down high-level research goals into individual tasks, allocating resources and coordinating specialized agents to work in parallel.

Since sharing early research last year, we’ve been developing and testing the system with scientists and research teams globally tackling complex scientific problems. Read about just a few ways it’s already having an impact:

Co-Scientist will be available to researchers through Hypothesis Generation, a new experimental tool developed across Google DeepMind, Google Research, Google Cloud and Google Labs. Learn more about Co-Scientist and how researchers are using it on the Google DeepMind blog.

Related stories