@umichkim: AI for Science is moving from “writing text” to “writing and testing scientific code.” A new Nature paper introduces ER…
Summary
A new Nature paper introduces ERA, an AI system that iteratively writes, runs, scores, and improves scientific code through tree search, moving AI for science from text generation to code testing.
View Cached Full Text
Cached at: 06/17/26, 06:02 PM
AI for Science is moving from “writing text” to “writing and testing scientific code.” A new Nature paper introduces ERA: an AI system that repeatedly writes code, runs it, scores it, and improves it through tree search. The key question is what we ask it to optimize. https://t.co/2xVo433aOn
Similar Articles
Towards End-to-End Automation of AI Research
A paper presenting The AI Scientist, a system that automates the entire research lifecycle from idea generation to peer review, demonstrating AI's growing capacity for scientific contribution.
@tom_doerr: Automates empirical research with 23,000 AI agent skills https://github.com/brycewang-stanford/Auto-Empirical-Research-…
Auto-Empirical-Research-Skills (AERS) is an open-source toolkit that automates the entire empirical research pipeline using 23,000+ AI agent skills, from data cleaning to submission-ready drafts.
@ai_suxiaole: Many AI tools can save researchers time, but most only solve one step: reading papers, writing code, polishing papers, or summarizing abstracts. Sakana AI's AI Scientist-v2 aims to be an AI system that runs the full research workflow, from generating research hypotheses to designing experiments...
Sakana AI has released AI Scientist-v2, an end-to-end automated research system that can autonomously go from generating research hypotheses to writing papers, and has been accepted by the ICLR2025 Workshop after peer review.
@JIACHENLIU8: AI4S research today: self-evolving loops, multi-agent systems, agent skills, science benchmarks etc. --> all to make li…
This article critiques current AI for Science (AI4S) research for focusing on compensating weaknesses of frontier models, arguing that the true bottleneck is the scientific ecosystem rather than individual AI scientist intelligence. It calls for a shift toward building an AI-native scientific ecosystem from first principles.
@_akhaliq: paper:
A paper introducing Arbor, an AI framework that enables autonomous scientific research by combining strategic coordination, isolated hypothesis testing, and a persistent knowledge tree to iteratively improve research outcomes across multiple domains.