English

AgenticSciML: Collaborative Multi-Agent Systems for Emergent Discovery in Scientific Machine Learning

Artificial Intelligence 2026-02-17 v2 Computational Engineering, Finance, and Science Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2511.07262,
  title  = {AgenticSciML: Collaborative Multi-Agent Systems for Emergent Discovery in Scientific Machine Learning},
  author = {Qile Jiang and George Karniadakis},
  journal= {arXiv preprint arXiv:2511.07262},
  year   = {2026}
}
R2 v1 2026-07-01T07:30:08.137Z