Problem
Research questions and friction points this paper is trying to address.
MOF simulations
workflow automation
computational materials science
expert decision-making
simulation accessibility
SimMOF: AI agent for Automated MOF Simulations
🤖 AI Summary
This work addresses the limited accessibility of metal–organic framework (MOF) simulations, which traditionally rely heavily on expert knowledge. To overcome this barrier, the authors propose a large language model–driven multi-agent system that autonomously executes end-to-end simulation workflows—from natural language queries through task planning, input generation, simulation execution, and result interpretation. By incorporating dependency-aware task decomposition and coordinated tool use, the system emulates human researchers’ decision-making processes, enabling cognitive autonomy and iterative refinement. Demonstrated on representative case studies, the framework efficiently handles complex MOF simulations, substantially lowering the entry barrier while enhancing scalability and usability. This approach establishes a novel paradigm for data-driven MOF research, making advanced computational exploration more accessible and systematic.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
AI agent
MOF simulation
large language model
automated workflow
natural language interface
🔎 Similar Papers
No similar papers found.
