LLM 智能体尝试改进地球系统模式参数化方案
Can LLM Agents Improve Imperfect Earth System Model Parameterizations?
用 10 个 LLM 自动写气象参数化代码，100 个方案里有 2 个误差打平了人工调优的版本，搞科研自动化的可以看看这篇。
arXiv 论文以暖雨碰并过程为测试案例，评估 LLM 智能体在地球系统模式（ESM）参数化开发中的能力，涉及文献综合、复现已发布参数化方案，并用可微 JAX 代码提出新的函数形式。实验在 10 个语言模型上重复进行，与高保真超液滴模拟对比。迭代反馈降低了其中 8 个模型的中位 rollout 误差。在 100 个无人值守生成的闭合格式中，有 2 个在留出模拟上的雨质量误差略低于精度最高的重调谐方案。
Can LLM Agents Improve Imperfect Earth System Model Parameterizations?
Earth system models (ESMs) rely on parameterizations to represent unresolved processes such as convection, cloud microphysics, and turbulence. However, translating advances in physical understanding into stable, validated parameterizations and integrating them into ESMs often takes years. Agentic AI could accelerate this process and enable more systematic exploration of design choices. Using warm-rain collision-coalescence as a test case, we evaluate agents' ability to synthesize scientific literature, reimplement published bulk parameterizations, and propose new functional forms as differentiable JAX code. We compare conventional parameterizations, data-driven emulators, and agent-generated closures against high-fidelity superdroplet simulations, repeating unattended experiments across ten language models. With expert guidance or iterative feedback, agents produced executable, differentiable, mass-conserving code, although unattended performance depended strongly on the scheme and language model. Iterative feedback lowered median rollout error for eight of ten models. Retuned physical schemes matched or outperformed many learned parameterizations at substantially lower computational cost, but two of 100 unattended agent-generated closures achieved slightly lower rain-mass error than the most accurate retuned scheme on held-out simulations.