发表机构
South China University of Technology; South China Normal University（华南理工大学; 华南师范大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出双智能体框架，将MetaBBO设计视为编码任务，通过递归自我改进实现开放式进化，自动生成优于人工基线的优化器变体，并支持跨领域快速适应。
AI 中文摘要
元黑箱优化（MetaBBO）是近期人工智能优化趋势中的亮点之一。该范式的双层工作流程利用元层面的可学习算法设计策略，以确保低层优化任务的性能和泛化提升。虽然MetaBBO有助于提升所得优化系统的性能下限，但目前它是手工制作且逐案例定制的，以适应不同的优化问题，这不可避免地引入了固有的主观性，从而限制了性能上限和实际可用性。在本文中，我们通过将MetaBBO的设计循环视为编码任务来解决这一问题，在此过程中，我们可以借助先进编码智能体的递归自我改进能力，将开放性引入MetaBBO。具体而言，我们提出了一个双智能体框架：i) 任务智能体通过代码进化不断改进目标MetaBBO方法的代码库；ii) 超智能体逐步修改任务智能体和自身，以提供开放式的设计行为；iii) 进化后的MetaBBO代码库被评估，所有执行中的信息被反馈给智能体，用于递归的自我参照改进。因此，给定一个朴素的MetaBBO模板，我们的框架自动化了设计进化，并发现了优于最新人工设计的MetaBBO基线的新变体。令人惊讶的是，实验结果还表明，我们的框架支持跨不同优化领域的快速适应。可靠的解释分析进一步揭示了在这种开放过程中出现的有趣设计原则。这项工作是对自动化设计复杂学习辅助优化算法的首次探索。
英文摘要
Meta-Black-Box Optimization (MetaBBO) is one of the highlights in the recent AI for Optimization trend. This paradigm's bi-level workflow leverages the learnable algorithm design policy at meta level to ensure the performance and generalization improvement on the low-level optimization task. While MetaBBO helps advance the performance lower bound of the resulted optimization system, it is currently handcrafted and customized case by case to adapt different optimization problems, which inevitably introduces inherent subjectivity and hence restricts the performance upper bound and usability in practice. In this paper, we address this issue by regarding MetaBBO's design loop as coding task, where we could introduce openendedness into MetaBBO with recursive self-improvement capability of advanced coding agents. Specifically, we propose a dual-agent framework: i) a task agent continuously refines the codebase of a target MetaBBO approach through code evolution; ii) a hyper agent progressively modifies the task agent and itself to provide open-ended design behavior; iii) the evolved MetaBBO codebase is evaluated and all in-execution information is fed back to the agents for recursive self-referential improvement. As a result, given a naive MetaBBO template, our framework automates a design evolution and finds novel variants superior to up-to-date human-made MetaBBO baselines. Surprisingly, the experimental results also demonstrate that our framework supports fast adaption across different optimization domains. Solid interpretation analysis further reveals interesting design principles emerge in such open-ended process. This work serves as the first exploration on automating design of complex learning-assisted optimization algorithms.
