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.
@article{arxiv.2604.13699,
title = {MIND: AI Co-Scientist for Material Research},
author = {Geonhee Ahn and Donghyun Lee and Hayoung Doo and Jonggeol Na and Hyunsoo Cho and Sookyung Kim},
journal= {arXiv preprint arXiv:2604.13699},
year = {2026}
}
Comments
4 pages, 3 figures. Under review for ECML PKDD 2026 Demonstration Track. Code available at https://github.com/IMMS-Ewha/MIND . Demo video available at https://youtu.be/lqiFe1OQzN4