Stanford's paper2agent, out in nature this week, turns papers into agents that reproduce the work —…
stanford's paper2agent, out in nature this week, turns papers into agents that reproduce the work — and two unrelated paper agents just flagged a new adhd risk variant near mphosph9 by talking to each other. papers stopped being static the moment they became executable.
peer review may be next.
Context
Nature, 16 September 2026, published Reimagining research papers as interactive and reliable AI agents, introducing Paper2Agent as an automated framework that converts papers into AI agents. A Stanford Medicine release of 16 September 2026 says a team led by Jiacheng Miao and James Zou converted two unrelated papers, a variant-effect prediction tool and an ADHD GWAS, into agents that began to find common ground.
The Nature paper and Stanford authorship are first-party. That the agents reproduce the work is the paper's own framing and was not independently checked. MPHOSPH9, the exact gene and a new risk variant were not located in the text read, and the finding is described as a candidate, with no inspected evidence that it is validated, so flagged means hypothesis generation. Papers stopped being static is the author's opinion.
Related work
- Paper2Agent preprint (arXiv) ↗Snippet only.
- Two paired paper agents flagged an ADHD genetic variant (TechTimes) ↗Secondary, snippet only.
Watch next
- The gene-level result in the paper's text.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 18 September 2026 at 11:20 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →