LLM Agents Perform Controlled Experiments Using Simulation Models

2026-08-22

AI Summary

本文提出一个多代理框架，使大型语言模型能够通过科学模拟模型进行受控实验，以优化制药过程设计，提高输出的具体性和实用性。

Abstract

Large language models (LLMs) have shown strong capabilities in reasoning, planning, and tool use, but many scientific and engineering tasks require more than plausible text and code generation. They require understanding how a system responds to intervention, which in practice depends on controlled experimentation. In this work, we propose a multi-agent framework that enables LLM agents to conduct controlled experiments with scientific simulation models for pharmaceutical process design. Given a user query and a baseline configuration, the system constructs a structured task representation, designs experiments, executes comparative simulation, interprets the resulting outcomes, and synthesizes evidence-based recommendations for process parameter optimization. By coupling language models with high-fidelity simulation models in an interactive agent framework, the proposed system supports reasoning through intervention, comparison, and observation. As a result, it produces more specific and actionable outputs than language-only reasoning. In an industrial application setting, this advantage is reflected in higher output specificity as well as improved user-rated correctness and helpfulness. Ablation studies and visualized case analyses further demonstrate the effectiveness and practical utility of simulation-integrated experimental reasoning.

Problem

• Large language models
• controlled experiments
• simulation models
• pharmaceutical process design
• intervention

Innovation

• multi-agent framework
• controlled experiments
• simulation models
• pharmaceutical process design
• intervention and comparison