LLM Agents Perform Controlled Experiments Using Simulation Models

The paper introduces a multi‑agent framework that lets large language models (LLMs) perform controlled experiments using scientific simulation models, specifically for pharmaceutical process design. Given a user query and baseline configuration, the system builds a structured task, designs and runs comparative simulations, interprets outcomes, and generates evidence‑based recommendations for optimizing process parameters. By integrating high‑fidelity simulations with LLMs, the approach yields more specific, actionable outputs and improves user‑rated correctness and helpfulness compared to language‑only reasoning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• benchmarks