SimMOF: AI agent for Automated MOF Simulations

arXiv cs.AI / 4/1/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisTools & Practical UsageModels & Research

共有:

Key Points

SimMOF is introduced as an LLM-based multi-agent framework that automates end-to-end metal-organic framework (MOF) simulation workflows from natural-language queries.
The system translates user requests into dependency-aware plans, generates runnable simulation inputs, and orchestrates multiple agents to execute simulations.
SimMOF also summarizes and analyzes results in a way that is aligned with what the user asked for, reducing the need for expert-driven workflow construction and parameter selection.
The article argues that SimMOF supports adaptive, “cognitively autonomous” iterative workflows that mimic human researchers’ decision-making behavior.
Case studies are presented to suggest SimMOF can serve as a scalable foundation for data-driven MOF research, where simulations have historically been hard to access.

Abstract

Metal-organic frameworks (MOFs) offer a vast design space, and as such, computational simulations play a critical role in predicting their structural and physicochemical properties. However, MOF simulations remain difficult to access because reliable analysis require expert decisions for workflow construction, parameter selection, tool interoperability, and the preparation of computational ready structures. Here, we introduce SimMOF, a large language model based multi agent framework that automates end-to-end MOF simulation workflows from natural language queries. SimMOF translates user requests into dependency aware plans, generates runnable inputs, orchestrates multiple agents to execute simulations, and summarizes results with analysis aligned to the user query. Through representative case studies, we show that SimMOF enables adaptive and cognitively autonomous workflows that reflect the iterative and decision driven behavior of human researchers and as such provides a scalable foundation for data driven MOF research.