MIND: AI Co-Scientist for Material Research

TL;DR

MIND is an AI framework that automates hypothesis validation in materials research by integrating LLMs, multi-agent collaboration, and machine learning-based in-silico experiments, with a user interface and modular design.

Contribution

It introduces a novel multi-agent pipeline for automated hypothesis testing in materials science, combining LLMs with scalable experimental modules.

Findings

Implemented a multi-agent system for hypothesis validation.

Integrated Machine Learning Interatomic Potentials for scalable experiments.

Provided a web interface for automated hypothesis testing.

Abstract

Large language models (LLMs) have enabled agentic AI systems for scientific discovery, but most approaches remain limited to textbased reasoning without automated experimental verification. We propose MIND, an LLM-driven framework for automated hypothesis validation in materials research. MIND organizes the scientific discovery process into hypothesis refinement, experimentation, and debate-based validation within a multi-agent pipeline. For experimental verification, the system integrates Machine Learning Interatomic Potentials, particularly SevenNet-Omni, enabling scalable in-silico experiments. We also provide a web-based user interface for automated hypothesis testing. The modular design allows additional experimental modules to be integrated, making the framework adaptable to broader scientific workflows. The code is available at: https://github.com/IMMS-Ewha/MIND, and a demonstration video at: https://youtu.be/lqiFe1OQzN4.