Excited to share our new papers at #ICLR2026 on
(multi-)agents, efficient reasoning, long context, better tokenizers and scientific applications 🚀

My awesome students and collaborators will be presenting them at the main conference this week; check it out! 👇

been using the paperclip.gxl.ai by @jameszou.bsky.social and im just blown away but how much better it makes cc as a research assistant. i feel like they solved something smoothly. an elegant example of 'you need to translate problems to something that a CLI solves'. researchers - try it

Did you know AI can predict disease from just one night’s sleep?

According to @jameszou.bsky.social , AI models can analyse sleep data to predict over 100 different diseases.

Explore the interview: t.co/qA1fUODuGC t.co/OhrbWuigDW

CellVoyager: AI CompBio agent generates new insights by autonomously analyzing biological data - Nature Methods CellVoyager is an artificial intelligence agent capable of exploring new biological hypotheses by autonomously analyzing single-cell RNA sequencing datasets and accounting for background information a...

In CellVoyager from @jameszou.bsky.social and teams AI agents pore over published papers. Seems intriguing to naive me that it can "uncover missing insights by autonomously analyzing biological data at scale. " 1/n www.nature.com/articles/s41...

Decoding the language of sleep with artificial intelligence Sleep is one of medicine's underused data streams. Clinically, disturbed sleep has often been treated as a symptom of a disorder, but sleep is also a physiological state in which brain, cardiac, respi...

The data from sleep is incredibly rich, a window into health and risk of many diseases, decoded by AI.
Our new essay today
@jameszou.bsky.social @thelancet.com
thelancet.com/journals/lan...

As speech models are being deployed in real-world taxi and emergency service settings, the failure to accurately transcribe named entities can cause delays and errors in critical settings.

We have posted a Research Assistant (LSRP1) position to work on aging and 'rejuvenation' using mouse models!! 🐭

careersearch.stanford.edu/jobs/life-sc...

Apply and join our awesome lab!! (please share) 😎

What do LLMs think about on their own, when we let them think freely?

We generated 250K “daydream” samples across models 🧠
GPT → coding
Qwen → multiple-choice math exams
Llama → literature
DeepSeek → math, religion, psychology

#Squidiff is highlighted on the cover of Nature Methods! Read about our diffusion model for single cells www.nature.com/articles/s41...

Great job Siyu He and all the wonderful collaborators!

🏆 Thank you @cp-patterns.bsky.social for selecting our work on LLM-assisted writing across society as a Best Paper of 2025! info.cell.com/collection-r...

AI model predicts disease risk while you sleep The first artificial intelligence model of its kind can predict more than 100 health conditions from one night’s sleep.

Nice Stanford article discussing our SleepFM AI: predicting diseases while you sleep news.stanford.edu/stories/2026...

The first sleep AI foundation model for predicting diseases was published today @naturemedicine.bsky.social
by @jameszou.bsky.social and colleagues
nature.com/articles/s41...
With Notebook LM, I made this infographic that tells the rich story pretty well

Artificial intelligence agents for biology - Nature Methods Artificial intelligence agents may have a transformative effect on how biological research is performed.

Thanks to Nature Methods for highlighting AI agents for biology (and the Virtual Lab) as a 2025 Method to Watch! www.nature.com/articles/s41...

Exploring the use of AI authors and reviewers at Agents4Science - Nature Biotechnology Nature Biotechnology - Exploring the use of AI authors and reviewers at Agents4Science

Exploring the use of AI authors and reviewers at Agents4Science - @jameszou.bsky.social go.nature.com/4j1O7a3

📣📣📣 Our second keynote speaker works on developing cutting-edge AI for biomedical applications. We're pleased to have James Zou (@jameszou.bsky.social) talk about "AI agents to accelerate scientific discoveries."

To know more about the talk, check out: 2025.jcdl.org/keynotes/

Schematic of cell differentiation prediction (a) and drug response prediction (b).

New paper out in @natmethods.nature.com from @elhamazizi.bsky.social, Kam Leong & @jameszou.bsky.social! The team developed Squidiff, a diffusion #AI model to predict cellular responses to environmental cues and accelerate #PrecisionMedicine.

Learn more: bit.ly/3WRPNsx

This is figure 1, which shows LMs struggle to affirm first-person beliefs in factually false scenarios.

Large language models (LLMs) may not reliably acknowledge a user’s incorrect beliefs, according to a paper in Nature Machine Intelligence. The findings highlight the need for careful use of LLM outputs in high-stakes decisions. go.nature.com/48VRpIQ 🧪

It’s here! #Agents4Science recording is now on YouTube!
🏆 3 Best Paper talks
⚡️ 11 Spotlights
🧠 Panel on the future of AI agent-driven science
📚 Lessons + surprises from this first-of-its kind conf

Full analysis of submissions + reviews coming soon! youtube.com/watch?v=7pXq...

AI bots wrote and reviewed all papers at this conference Event will assess how reviews by models compare with those written by humans.

Next week @jameszou.bsky.social & colleagues will host a conference where all the papers are written by AI agents & reviewed by them too.

What do you reckon? A good chance to put AIs through their paces? Or a way to divert AI slop from elsewhere? 🧪🤖

My story here:
www.nature.com/articles/d41...

A circular flow diagram that compares current and proposed practices for LLM development using data from adopters and non-adopters. Three gray boxes represent current practices: “R&D,” “Chat Models,” and “Adopters’ Needs and Usage Data,” connected in a clockwise loop with black arrows. A blue box labeled “Non-adopters’ Needs and Usage Data” adds a proposed feedback path, shown with blue arrows, linking non-adopter data back to R&D and adopters’ data.

As of June 2025, 66% of Americans have never used ChatGPT.

Our new position paper, Attention to Non-Adopters, explores why this matters: AI research is being shaped around adopters—leaving non-adopters’ needs, and key LLM research opportunities, behind.

arxiv.org/abs/2510.15951

"We found a troubling emergent behavior in LLM.
—When LLMs compete for social media likes, they start making things up.
—When they compete for votes, they turn inflammatory/populist.
—When optimized for audiences, LLMs inadvertently become misaligned."
→ Moloch's Bargain @jameszou.bsky.social #AI

First page of article: "The widespread adoption of large language model-assisted writing across society" published in Patterns

#AI wrote nearly a quarter of corporate press releases in 2024 and the number is likely to keep rising. spkl.io/63324ATfBo

Weixin Liang, @jameszou.bsky.social & colleagues
@cp-patterns.bsky.social

James Zou, Ph.D

@stanforddeptmed.bsky.social Biomedical Informatics Research Colloquia

“AI Agents to Automate Biomedical Discoveries”
@jameszou.bsky.social James Zou, Ph.D

Thursday, September 25th, 2025
12:00 to 1:00 pm PST

stanford.zoom.us/j/9788759601...

Webinar ID: 978 8759 6012
Webinar Passcode: 420642

Fantastic talk by @stanford.edu's @jameszou.bsky.social for the first Innovation Initiative Distinguished Lecture at @whiteheadinstitute.bsky.social. A fascinating look at how to use #AI to build intelligent research teams that can tackle open-ended scientific problems. #WhiteheadInstitute #MIT

🧠Can AI agents predict #Alzheimers? Participate in our DREAM challenge agentic track to find out!

We provide unique training + test data for AI agents: snRNA-seq, IHC, stage, etc synapse.org/Synapse:syn6...

Also co-submit your agent paper to agents4science.stanford.edu

Researchers create ‘virtual scientists’ to solve complex biological problems Stanford Medicine researchers created a team of virtual scientists backed by artificial intelligence to help solve problems in their real-world lab.

“Good science happens when we have deep, interdisciplinary collaborations, and often that’s one of the main bottlenecks and challenging parts of research,” said HAI Faculty Affiliate @jameszou.bsky.social who led a study on AI-driven virtual labs: med.stanford.edu/news/all-new...

Researchers create ‘virtual scientists’ to solve complex biological problems An AI lab developed by Stanford Medicine researchers has already shown promising results, generating ideas for a more effective COVID-19 vaccine in just a few days.

Nice @stanforduniversity.bsky.social article profiling our #VirtualLab of AI scientists news.stanford.edu/stories/2025...

Figure 1. An Overview of the Fine-Tuning Case Study.

Figure 2. Performance of Fine-Tuned Large Language Models on Each Medical Dataset.

Figure 3. Model Performance on MedQA after Updating.

Case Study by Eric Wu, PhD, Kevin Wu, PhD, and James Zou, PhD: Limitations of Learning New and Updated Medical Knowledge with Commercial Fine-Tuning Large Language Models nejm.ai/4nTx1Np

@jameszou.bsky.social #AI #MedSky

GitHub - zou-group/virtual-lab: A virtual lab of LLM agents for science research A virtual lab of LLM agents for science research. Contribute to zou-group/virtual-lab development by creating an account on GitHub.

The Virtual Lab is open source and can be applied to many problems! github.com/zou-group/vi...

👏Great job @kylewswanson.bsky.social John Pak, Wes Wu, Nash Bulaong @czbiohub.bsky.social

⚡️Thrilled that #VirtualLab is published in @nature.com! www.nature.com/articles/s41...

We created a team of AI agents to mirror my Stanford lab 🤖. Led by a PI agent, the AI scientists ran their own group meetings and discovered effective binders to new CoVID variants that we validated.