Efficiently optimizing battery charging protocols is challenging because each evaluation is slow, costly, and non-differentiable. Many existing approaches address this difficulty by heavily constraining the protocol search space, which limits the diversity of protocols that can be explored, preventing the discovery of higher-performing solutions. We introduce two gradient-free, LLM-driven closed-loop methods: Prompt-to-Optimizer (P2O), which uses an LLM to propose the code for small neural-network-based protocols, which are then trained by an inner loop, and Prompt-to-Protocol (P2P), which simply writes an explicit function for the current and its scalar parameters. Across our case studies, LLM-guided P2O outperforms neural networks designed by Bayesian optimization, evolutionary algorithms, and random search. In a realistic fast charging scenario, both P2O and P2P yield around a 4.2 percent improvement in state of health (capacity retention based health metric under fast charging cycling) over a state-of-the-art multi-step constant current (CC) baseline, with P2P achieving this under matched evaluation budgets (same number of protocol evaluations). These results demonstrate that LLMs can expand the space of protocol functional forms, incorporate language-based constraints, and enable efficient optimization in high cost experimental settings.

翻译：高效优化电池充电协议具有挑战性，因为每次评估过程缓慢、成本高昂且不可微分。现有方法大多通过严格约束协议搜索空间来应对这一难题，但这限制了可探索协议的多样性，阻碍了发现更高性能解决方案的可能性。我们提出了两种基于大型语言模型（LLM）的无梯度闭环方法：提示到优化器（P2O）——利用LLM生成小型神经网络协议代码，并通过内循环进行训练；以及提示到协议（P2P）——直接编写电流及其标量参数的显式函数。在案例研究中，LLM引导的P2O在性能上超越了贝叶斯优化、进化算法和随机搜索设计的神经网络。在现实快充场景中，相较于最先进的多步恒流基准方案，P2O和P2P在健康状态（基于快充循环容量保持的健康指标）上均实现约4.2%的提升，其中P2P在相同评估预算（协议评估次数相同）下达成该成果。这些结果表明，LLM能够扩展协议函数形式空间，整合基于语言的约束条件，并在高成本实验环境中实现高效优化。