Virtuous Machines: Towards Artificial General Science

2025-08-18

AI Summary

Current scientific AI systems suffer from narrow domain specificity and heavy reliance on human intervention, limiting their capacity to address the dual challenges of exponential literature growth and increasing disciplinary silos. To overcome these limitations, we propose the first domain-agnostic autonomous scientific agent capable of executing an end-to-end research pipeline—including hypothesis generation, experimental design, data collection (including online psychological experiments), automated analysis, and scholarly manuscript drafting. Our agent uniquely performs, for the first time, a fully embodied empirical psychological study autonomously—integrating theoretical reasoning, methodological rigor, and real-time experimental validation. Built upon a self-directed agent architecture, it unifies dynamic code generation, multimodal data analysis, and integration with online experimental platforms to enable iterative scientific decision-making. We demonstrate its efficacy through three original psychological studies, yielding 288 newly collected participant responses; the system autonomously generated both analytical code and complete academic manuscripts, achieving research proficiency comparable to that of experienced investigators.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Intelligent Robots: Embodied AI

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation

Abstract

Artificial intelligence systems are transforming scientific discovery by accelerating specific research tasks, from protein structure prediction to materials design, yet remain confined to narrow domains requiring substantial human oversight. The exponential growth of scientific literature and increasing domain specialisation constrain researchers' capacity to synthesise knowledge across disciplines and develop unifying theories, motivating exploration of more general-purpose AI systems for science. Here we show that a domain-agnostic, agentic AI system can independently navigate the scientific workflow - from hypothesis generation through data collection to manuscript preparation. The system autonomously designed and executed three psychological studies on visual working memory, mental rotation, and imagery vividness, executed one new online data collection with 288 participants, developed analysis pipelines through 8-hour+ continuous coding sessions, and produced completed manuscripts. The results demonstrate the capability of AI scientific discovery pipelines to conduct non-trivial research with theoretical reasoning and methodological rigour comparable to experienced researchers, though with limitations in conceptual nuance and theoretical interpretation. This is a step toward embodied AI that can test hypotheses through real-world experiments, accelerating discovery by autonomously exploring regions of scientific space that human cognitive and resource constraints might otherwise leave unexplored. It raises important questions about the nature of scientific understanding and the attribution of scientific credit.

Problem

• AI systems are confined to narrow scientific domains
• Exponential growth of literature constrains cross-disciplinary synthesis
• General-purpose AI needed for autonomous scientific workflow navigation

Innovation

• Domain-agnostic agentic AI system
• Autonomous hypothesis-to-manuscript scientific workflow
• Real-world experimental execution with human participants