让光子晶体光纤设计能积累经验，像人一样越用越快越准。
Learning Design Skills as Memory Policies for Agentic Photonic Inverse Design
- 用记忆库存设计技能，结合强化学习选择最佳方案。
- 在2507次设计迭代中实现更优的性能与效率平衡。
- 适合需要反复优化的物理仿真设计任务，如光纤工程。
光子晶体光纤（PCF）逆向设计因需满足多重光学目标且依赖昂贵的电磁仿真而困难重重。现有方法仅提升预测或单次参数推荐，未能积累可复用的设计知识。本文将PCF逆向设计建模为记忆-策略学习问题，提出SkillPCF框架：融合物理引导的记忆技能库、强化学习驱动的技能选择及模拟器验证的技能演化。构建了包含479条专家交互轨迹（2507个设计片段）和553个依赖记忆的评估查询的真实数据集，覆盖色散工程、损耗优化与多目标设计。在多个大模型基线和经典方法上实验表明，SkillPCF在实际仿真预算下实现了更优的设计质量与效率权衡，验证了记忆-技能学习范式在物理感知光子设计中的有效性。
原文摘要 · Abstract (English)
Photonic crystal fiber (PCF) inverse design remains challenging because candidate geometries must satisfy coupled optical targets under expensive electromagnetic simulation. Existing pipelines improve surrogate prediction or one-shot parameter recommendation, but they do not accumulate reusable design knowledge across iterative trials. We formulate PCF inverse design as a memory-policy learning problem and propose SkillPCF, a closed-loop agent framework that combines a physics-guided memory skill bank, reinforcement-learned skill selection, and simulator-grounded skill evolution. We further construct a real-world dataset with 479 expert interaction traces (2,507 spans) and 553 memory-dependent evaluation queries covering dispersion engineering, loss optimization, and multi-objective design. Experiments across multiple LLM backbones and classical baselines show that SkillPCF achieves stronger design-quality and efficiency trade-offs under practical simulation budgets, demonstrating the effectiveness of our proposed memory-skill learning paradigm for physics-aware PCF inverse design.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。