Saved in:
Bibliographic Details
Main Authors: Ahn, Geonhee, Lee, Donghyun, Doo, Hayoung, Na, Jonggeol, Cho, Hyunsoo, Kim, Sookyung
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.13699
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910131202031616
author Ahn, Geonhee
Lee, Donghyun
Doo, Hayoung
Na, Jonggeol
Cho, Hyunsoo
Kim, Sookyung
author_facet Ahn, Geonhee
Lee, Donghyun
Doo, Hayoung
Na, Jonggeol
Cho, Hyunsoo
Kim, Sookyung
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13699
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MIND: AI Co-Scientist for Material Research
Ahn, Geonhee
Lee, Donghyun
Doo, Hayoung
Na, Jonggeol
Cho, Hyunsoo
Kim, Sookyung
Multiagent Systems
Artificial Intelligence
Computational Engineering, Finance, and Science
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.
title MIND: AI Co-Scientist for Material Research
topic Multiagent Systems
Artificial Intelligence
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2604.13699