AI That Runs Its Own Experiments to Improve Drug Manufacturing

Researchers propose a multi-agent framework that lets LLM agents run controlled experiments using simulation models for pharmaceutical process design. Given a query and a baseline configuration, the system builds a structured task representation, designs experiments, executes comparative simulations, interprets the results, and synthesizes evidence-based recommendations for process parameter optimization. By coupling language models with high-fidelity simulation models, the framework supports reasoning through intervention, comparison, and observation, producing more specific and actionable outputs than language-only reasoning. In an industrial application setting, it demonstrated higher output specificity and improved user-rated correctness and helpfulness, with ablation studies and visualized case analyses also showing its effectiveness and practical utility.