AI Judge changed title after evaluation, original title: "FutureHouse and Google DeepMind publish multi-agent AI systems for end-to-end scientific discovery in new Nature papers, with Robin identifying ripasudil for macular degeneration and ERA generating 40 novel single-cell methods"
Nature comment examines AI narrowing research questions and tacit skill development.
A big day for multi-agent AI to accelerate biomedical discovery, hypothesis generation, designing experiments with proof points of new candidate drugs (cancer, fibrosis, macular degeneration, antimicrobial resistance, and more) 2 @Nature reports @GoogleDeepMind @FutureHouseSF https://www.nature.com/articles/s41586-026-10658-6 https://www.nature.com/articles/s41586-026-10652-y
Positive users celebrated FutureHouse's Robin multi-agent AI system and its Nature publication for advancing drug discovery, while negative users dismissed the work as hype or an attempt to mislead investors.
Important editorial @Nature on the new "AI-scientist" papers "AI scientists can and should empower human researchers. They cannot and should not replace them." https://www.nature.com/articles/d41586-026-01551-3
A big day for multi-agent AI to accelerate biomedical discovery, hypothesis generation, designing experiments with proof points of new candidate drugs (cancer, fibrosis, macular degeneration, antimicrobial resistance, and more) 2 @Nature reports @GoogleDeepMind @FutureHouseSF https://www.nature.com/articles/s41586-026-10658-6 https://www.nature.com/articles/s41586-026-10652-y
Congrats to @GoogleDeepMind on their paper in Nature today! Great to see them prove out Co-Scientist in the lab.
https://www.nature.com/articles/s41586-026-10644-y
Lots of news today. Don't have energy to write a hit tweet, so here's list
1. Our work on doing lab-in-the-loop with agents was published in Nature 2. We announced our first research partnership with a pharmaceutical company 3. We made new persistent code-writing agent
We're pleased to share our first @Nature paper: Robin is the first multi-agent system for discovery in biology that integrates novel hypothesis generation with experimental data analysis in one continuous workflow.
In this study, our team, including ophthalmologist @agreeb66, applied Robin to dry age-related macular degeneration, a leading cause of irreversible sight loss with limited treatment options. The system proposed drug-repurposing hypotheses, which were then tested experimentally in the lab.
Robin developed the experimental strategy for therapeutic hypothesis generation, proposed follow-up experiments, and extracted actionable insights from the resulting data, including validation in primary human retinal pigment epithelium (RPE) stem cells.
Robin also proposed a mechanism of enhancing RPE phagocytosis by modulating the cells circadian rhythm using an experimental drug, KL001, that has never before been used in humans or proposed for AMD. To our knowledge, this mechanism had not previously been proposed.
This work points to the future of AI-enabled science: systems that connect insights across fields, surface new mechanisms, and turn existing knowledge into testable hypotheses.
It also represents the broader opportunity FutureHouse is building toward: AI that helps science cross disciplinary boundaries and move from literature to experiment to discovery. https://www.nature.com/articles/s41586-026-10652-y
Our paper “Accelerating scientific discovery with Co-Scientist” is published today in @Nature. Read it here: https://www.nature.com/articles/s41586-026-10644-y and learn more about our real-world partnerships on the DeepMind blog: https://deepmind.google/blog/co-scientist-a-multi-agent-ai-partner-to-accelerate-research/
Our paper on Robin is out at Nature! Robin was the first multiagent system for end-to-end biological research, which we preprinted last year, and was published back to back with Google's awesome Coscientist from @vivnat. Great validation, and major congratulations to the team.
At the same time concerns about uncritical adoption, need for guard rails “There is growing evidence that LLM-driven increases in scientific productivity often come at a cost.”https://www.nature.com/articles/d41586-026-01557-x
A big day for multi-agent AI to accelerate biomedical discovery, hypothesis generation, designing experiments with proof points of new candidate drugs (cancer, fibrosis, macular degeneration, antimicrobial resistance, and more) 2 @Nature reports @GoogleDeepMind @FutureHouseSF https://www.nature.com/articles/s41586-026-10658-6 https://www.nature.com/articles/s41586-026-10652-y
Here's our engineering blog post with how we actually did all this: https://labs.edisonscientific.com/research/how-we-built-kosmos/
Lots of news today. Don't have energy to write a hit tweet, so here's list
1. Our work on doing lab-in-the-loop with agents was published in Nature 2. We announced our first research partnership with a pharmaceutical company 3. We made new persistent code-writing agent
Our agents can make real discoveries! One year of peer-review, but this work was accepted in @Nature . Huge congrats to the team, especially @agreeb66 who patiently worked on follow-up experiments for months. And here's a pics of some authors in the lab where we did the work
Incredible body of work by @EdisonSci announced today including a pharma deal. Proud to have them as part of the @NVIDIA ventures portfolio
Lots of news today. Don't have energy to write a hit tweet, so here's list
1. Our work on doing lab-in-the-loop with agents was published in Nature 2. We announced our first research partnership with a pharmaceutical company 3. We made new persistent code-writing agent
@SGRodriques @FutureHouseSF @vivnat @alan_karthi @GoogleDeepMind Good explainer of the significance of these reports, @heidiledford @Nature https://www.nature.com/articles/d41586-026-01596-4
Congrats to @SGRodriques and team @FutureHouseSF, @vivnat, @alan_karthi and team @GoogleDeepMind!
Congrats to @SGRodriques and team @FutureHouseSF, @vivnat, @alan_karthi and team @GoogleDeepMind!
A big day for multi-agent AI to accelerate biomedical discovery, hypothesis generation, designing experiments with proof points of new candidate drugs (cancer, fibrosis, macular degeneration, antimicrobial resistance, and more) 2 @Nature reports @GoogleDeepMind @FutureHouseSF https://www.nature.com/articles/s41586-026-10658-6 https://www.nature.com/articles/s41586-026-10652-y
Check it out here: https://www.nature.com/articles/s41586-026-10652-y
Our paper on Robin is out at Nature! Robin was the first multiagent system for end-to-end biological research, which we preprinted last year, and was published back to back with Google's awesome Coscientist from @vivnat. Great validation, and major congratulations to the team.
Yeah, this is very interesting pattern. Glad that @Nature is featuring this nice work. Cannot wait to read them in detail!
Very interesting. Three papers on agentic Science were just published in Nature today.
Been building in this exact space for a while now—my PhD thesis title is literally: "From AI for Genomics to Agentic Science." 🧐
More to come. 🚀
Looks like nice progress from @EdisonSci folks!
Here's our engineering blog post with how we actually did all this: https://labs.edisonscientific.com/research/how-we-built-kosmos/
@andrewwhite01 @Nature @agreeb66 Congrats!! 1 year for reviewing is insane…
@EricTopol @Nature While AI accelerates discovery at the research level, most patients are still waiting years to benefit. 3 markers available TODAY that already proxy biological age — numbers and thresholds 👇
@EricTopol @Nature @GoogleDeepMind @FutureHouseSF On the multi agent system, please read the details about Finch, the "analyst" agent. It doesn't make for good reading!
Co-Scientist is a multi-agentic AI powered by Gemini acts as a collaborative research partner. It generates, debates, and evolves novel hypotheses.
@andrewwhite01 Big congratulations!
