Scientific Machine Learning (SciML) integrates data-driven inference with physical modeling to solve complex problems in science and engineering. However, the design of SciML architectures, loss formulations, and training strategies remains an expert-driven research process, requiring extensive experimentation and problem-specific insights. Here we introduce AgenticSciML, a collaborative multi-agent system in which over 10 specialized AI agents collaborate to propose, critique, and refine SciML solutions through structured reasoning and iterative evolution. The framework integrates structured debate, retrieval-augmented method memory, and ensemble-guided evolutionary search, enabling the agents to generate and assess new hypotheses about architectures and optimization procedures. Across physics-informed learning and operator learning tasks, the framework discovers solution methods that outperform single-agent and human-designed baselines by up to four orders of magnitude in error reduction. The agents produce novel strategies -- including adaptive mixture-of-expert architectures, decomposition-based PINNs, and physics-informed operator learning models -- that do not appear explicitly in the curated knowledge base. These results show that collaborative reasoning among AI agents can yield emergent methodological innovation, suggesting a path toward scalable, transparent, and autonomous discovery in scientific computing.

翻译：科学机器学习（SciML）将数据驱动的推断与物理建模相结合，以解决科学与工程中的复杂问题。然而，SciML 的架构设计、损失函数构建以及训练策略仍然是一个专家驱动的研究过程，需要大量的实验和针对具体问题的深刻见解。本文提出 AgenticSciML，一种协作多智能体系统，其中超过 10 个专门化的 AI 智能体通过结构化推理与迭代进化，协作提出、批判并改进 SciML 解决方案。该框架集成了结构化辩论、检索增强的方法记忆以及集成引导的进化搜索，使智能体能够生成并评估关于架构与优化过程的新假设。在物理信息学习与算子学习任务中，该框架发现的求解方法在误差降低方面优于单智能体及人工设计的基线方法，提升幅度高达四个数量级。智能体产生了新颖的策略——包括自适应专家混合架构、基于分解的 PINNs 以及物理信息算子学习模型——这些策略并未明确出现在经过整理的知识库中。这些结果表明，AI 智能体间的协作推理能够产生涌现式的方法创新，为科学计算中可扩展、透明且自主的发现指明了一条路径。