HALO：用于纳米光子设计的物理感知大语言模型智能体框架
HALO: A Physics-Aware LLM Agent Framework for Nanophotonic Design
浏览论文内容
中文总结 AI 辅助
该研究提出HALO框架及52任务基准HALO-Bench，对比三类规划器配置，发现固定结构化工作流效率最高，自主编码成功率更高但故障更多，复用失败轨迹可减少迭代与令牌使用，明确了科学智能体的相关权衡。
中文摘要 AI 辅助
语言模型近期已被应用于纳米光子设计，但目前仍不清楚它们能否可靠地将光学目标转化为可用于模拟的设计、执行电磁分析，并根据数值反馈修正决策。我们提出了HALO，这是一种物理感知框架，在迭代设计循环中将大语言模型规划器与类型化设计规范、电磁模拟、诊断评估以及可选的过往失败轨迹复用相结合。我们还提出了HALO-Bench，这是一个包含52项任务的基准，涵盖实验室衍生、论文衍生和开放式纳米光子设计任务，采用统一评估协议。我们比较了三种规划器配置：固定结构化工作流、使用相同模拟接口的自主结构化智能体，以及直接编写并执行模拟代码的自主编码智能体。固定结构化工作流的令牌效率最高，且未观察到代码或路径级故障；而自主编码在使用更强模型时可实现更高的任务成功率，但代价是出现更多操作故障。我们还研究了过往失败轨迹的复用：在针对性多轮任务中，检索到的失败反馈减少了首次成功所需的迭代次数和总令牌使用量。这些结果阐明了科学智能体中显式接口、自主执行和可复用设计经验之间的权衡。
英文摘要
Language models have recently been applied to nanophotonic design, but it remains unclear whether they can reliably translate optical objectives into simulation-ready designs, execute electromagnetic analysis, and revise decisions from numerical feedback. We introduce HALO, a physics-aware framework that couples language-model planners with typed design specifications, electromagnetic simulation, diagnostic evaluation, and optional reuse of prior failure trajectories in an iterative design loop. We further introduce HALO-Bench, a 52-task benchmark spanning lab-derived, paper-derived, and open-ended nanophotonic design tasks under a shared evaluation protocol. We compare three planner configurations: a Fixed Structured Workflow, an Autonomous Structured Agent using the same simulation interface, and an Autonomous Coding Agent that directly writes and executes simulation code. The Fixed Structured Workflow is the most token-efficient and exhibits no observed code- or path-level failures, while autonomous coding can achieve higher task success with stronger models at the cost of additional operational failures. We also study reuse of prior failed trajectories. On targeted multi-round tasks, retrieved failure feedback reduces both iterations to first success and total token use. These results clarify the tradeoffs between explicit interfaces, autonomous execution, and reusable design experience in scientific agents.
