Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents

TL;DR

Curie is an AI framework that automates scientific experimentation with enhanced rigor, reliability, control, and interpretability, demonstrated by improved performance on a novel benchmark across multiple computer science domains.

Contribution

We introduce Curie, an AI agent framework that embeds rigor into scientific experiments through specialized modules, advancing automation and reliability in scientific research.

Findings

3.4× improvement over baseline in answering experimental questions

Effective integration of rigor modules enhances experiment reliability

Open-sourced implementation available for community use

Abstract

Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing capabilities of large language models (LLMs) in automating different aspects of the scientific process, automating rigorous experimentation remains a significant challenge. To address this gap, we propose Curie, an AI agent framework designed to embed rigor into the experimentation process through three key components: an intra-agent rigor module to enhance reliability, an inter-agent rigor module to maintain methodical control, and an experiment knowledge module to enhance interpretability. To evaluate Curie, we design a novel experimental benchmark composed of 46 questions across four computer science domains, derived from influential research papers, and widely adopted open-source projects. Compared to the strongest baseline tested, we achieve a 3.4$\times$ improvement in correctly answering experimental questions. Curie is open-sourced at https://github.com/Just-Curieous/Curie.