Search papers, labs, and topics across Lattice.
The paper introduces MIND, a multi-agent, LLM-driven framework for automated hypothesis validation in materials research. MIND refines hypotheses, conducts in-silico experiments using Machine Learning Interatomic Potentials (specifically SevenNet-Omni), and validates results through debate among agents. This integrated system provides a web interface for automated hypothesis testing and is designed for modular expansion to incorporate additional experimental modules.
Forget lab coats: MIND lets LLMs autonomously formulate and experimentally validate materials science hypotheses, potentially accelerating discovery.
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.
