LensDesigner：一种用于光学镜头设计的自我改进智能体
LensDesigner: A Self-Improving Agent for Optical Lens Design
- INSAIT, Sofia University “St. Kliment Ohridski”（索非亚大学圣克莱门特·奥赫里德分校INSAIT）
- Zhejiang University（浙江大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出LensDesigner，一种模仿专家光学设计师工作流程的自主智能体框架，通过构建LensLib100K库和光学感知检索解决冷启动问题，并在物理模拟环境中结合课程引导的自我进化机制，在LensArena基准的120个任务上显著优于现有基线算法。
AI中文摘要：
光学镜头设计是一个复杂的、非凸的优化挑战，严重依赖人类经验和直觉。现有的基于优化的自动镜头设计方法在缺乏细致手动调参的情况下，难以在庞大的参数空间中进行有效导航。在本文中，我们提出了LensDesigner，一个自主智能体框架，它模仿了专家光学设计师的问题解决工作流程。为了克服初始冷启动问题，我们构建了LensLib100K，一个广泛的光学镜头库，并采用光学感知检索来提供物理上有效的结构种子。在交互式物理模拟环境中，智能体执行宏观编排，同时接收即时光学反馈。此外，我们引入了一种由课程智能体引导的持续自我进化机制。通过迭代解决难度逐渐增加的设计任务，智能体自主提取、积累和重用设计启发式，从而有效地随时间演化其光学镜头设计专业知识。在评估层面，我们引入了LensArena，一个标准化的评估基准，包含120个多样化的光学设计任务，涵盖极端配置。在该基准上的大量实验表明，LensDesigner显著优于公开可用的基线算法，实现了更高的成功率和优化效率。我们希望这项工作能为智能光学这一新兴领域带来启示。代码将公开提供。
英文摘要：
Optical lens design is a complex, non-convex optimization challenge that relies heavily on human experience and intuition. Existing optimized-based automatic lens design methods struggle to navigate this vast parameter space without meticulous manual tuning. In this paper, we present LensDesigner, an autonomous agent framework that mirrors the problem-solving workflow of expert opticians. To overcome the initial cold start problem, we construct LensLib100K, an extensive optical lens library, and employ Optics-Aware Retrieval to supply physically valid structural seeds. Within an interactive physical simulation environment, the agent executes macroscopic orchestration while receiving immediate optical feedback. Furthermore, we introduce a continuous self-evolving mechanism guided by a curriculum agent. By iteratively solving design tasks with progressively increasing difficulty, the agent autonomously extracts, accumulates, and reuses design heuristics, effectively evolving its optical lens design expertise over time. At the evaluation level, we introduce LensArena, a standardized evaluation benchmark comprising $120$ diverse optical design tasks, covering extreme configurations. Extensive experiments on this benchmark demonstrate that LensDesigner significantly outperforms publicly available baseline algorithms, achieving superior success rates and optimization efficiency. We hope this work sheds light on the emerging field of intelligent optics. The code will be publicly available.
