@VraserX: Stanford turned scientific papers into AI agents that can reproduce the research and talk to other paper agents. Two ag…
Summary
Stanford researchers have created AI agents from scientific papers that can autonomously reproduce experiments and communicate with each other, leading to the discovery of a new genetic connection to ADHD risk.
View Cached Full Text
Cached at: 09/22/26, 11:46 AM
Stanford turned scientific papers into AI agents that can reproduce the research and talk to other paper agents.
Two agents built from unrelated studies then surfaced a previously unreported genetic connection to ADHD risk.
This is such a better vision for AI science than “chat with a PDF.”
Make human knowledge active.
Similar Articles
@StanfordMed: https://x.com/StanfordMed/status/2080452706385416506
Researchers are exploring agentic AI as co-scientists that can independently assist with ideation, hypothesis generation, and accelerating scientific exploration in biomedical research.
@dair_ai: Can coding-agents replicate scientific ML papers? We know this is possible because we can already do this @dair_ai. Sti…
This paper introduces 'Paper-replication', a workflow for coding agents that systematically replicates scientific machine learning papers by turning each claim into a target with recorded evidence, and demonstrates across twelve runs that all workspaces and targets are completed.
Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents
Paper2Agent is an automated framework that converts research papers into interactive AI agents to enhance knowledge dissemination and enable complex scientific queries through natural language.
@EricTopol: Just published @ScienceMagazine Impressively broad range of life science research getting done autonomously with agenti…
A paper published in Science Magazine demonstrates a broad range of life science research being conducted autonomously using agentic AI to accelerate discovery.
@rohanpaul_ai: New paper from Anthropic + University in Switzerland. AI agents can apparently persuade each other to adopt and keep sp…
New research from Anthropic and a Swiss university shows AI agents can persuade each other to adopt and spread unwanted goals like a natural-language worm, with persistence through self-modifiable files, but simple warnings can stop the attacks.