Molecular dynamics (MD) is the canonical in-silico method for atomistic molecular science, simulating molecular behavior from first-principle physics. Designing an MD pipeline for a new system requires substantial expert knowledge: running it on even one molecule is expensive, ruling out trial-and-error. We automate this expert pipeline-design process with an LLM agent. Unlike existing MD agents that orchestrate a predefined tool set, we treat pipeline design as open-ended code generation in which the agent's behavior is reshaped online by verbal reward. Specifically, we build MDForge, an LLM agent whose in-context update rule densifies the sparse reward via a multi-agent debate among physics experts. On three SAMPL host-guest binding free-energy benchmarks, MDForge automatically designs MD pipelines competitive with human experts. Deployed on a library of unseen candidate guests, its CB[7] pipeline discovers a novel binder that wet-lab competition NMR confirms is a high-affinity, picomolar CB[7] binder. Our data and code are available at https://github.com/Zehong-Wang/MDForge.

翻译：[translated abstract in Chinese] 分子动力学（MD）是基于第一性原理物理学模拟分子行为的原子分子科学经典计算方法。为新系统设计MD流程需要大量专业知识：即使在一个分子上运行该流程也代价高昂，从而排除了试错法的可行性。我们利用大语言模型（LLM）智能体来自动化这一专家级流程设计过程。与现有通过编排预定义工具集进行操作的MD智能体不同，我们将流程设计视为开放式代码生成任务，其中智能体的行为通过在线口头奖励进行动态调整。具体而言，我们构建了MDForge——一个LLM智能体，其通过物理学专家之间的多智能体辩论，将稀疏奖励信号密集化，从而实现上下文更新规则。在三个SAMPL主客体结合自由能基准测试中，MDForge自主设计的MD流程达到了与人类专家相媲美的水平。将该方法部署于未见过的候选客体分子库后，其生成的CB[7]流程发现了一种新型结合物——经湿实验竞争性NMR验证，该结合物为高亲和力、皮摩尔级别的CB[7]配体。我们的数据和代码已开源：https://github.com/Zehong-Wang/MDForge。