New AI agent SimMOF automates complex metal-organic framework simulations using large language models to eliminate need for expert computational specialists.

SimMOF uses a large language model-based multi-agent framework to automate end-to-end MOF simulation workflows from natural language user queries

The system translates user requests into dependency-aware plans, generates runnable inputs, and orchestrates multiple agents to execute simulations

Addresses accessibility barriers by eliminating need for expert decisions on workflow construction, parameter selection, and tool interoperability

Demonstrates adaptive, cognitively autonomous workflows that mirror the iterative, decision-driven behavior of human computational researchers