让代码片段可复用，提升自动算法设计的效率与可解释性
PACE: Primitive-Aware Code Evolution for Automated Algorithm Design
- 将算法拆解为可复用的独立代码单元（EAPs），实现局部逻辑持久化
- 在4个任务中生成性能媲美人工设计的算法，且关键组件可跨程序迁移
- 用基于相对性能的智能选择机制，无需额外数据即可优化组件使用
基于大语言模型的自动化算法设计通常以完整程序为单位进行演化。这种整体视角虽简化了搜索空间，却将有用的部分逻辑与宿主程序绑定，导致整体程序被丢弃时，有价值的代码片段也随之消失，难以评估各算法组件的贡献。为此，我们提出一种原始代码感知的演化方法（PACE），通过将局部逻辑表示为称为可执行算法原语（EAPs）的持久单元，实现其与完整程序的解耦。PACE维护一个动态的EAP集合，利用具备结构保证的原语感知算子驱动算法演化，确保这些组件的保留与跨程序转移。为有效评估，PACE采用基于泰普森采样的策略，依据父代相对性能提升指导原语选择，无需额外评估数据集。在四个任务上的实验表明，PACE能有效发现具有竞争力的算法，同时结构化地保留有价值的算法组件。
原文摘要 · Abstract (English)
Large Language Model (LLM)-based automated algorithm design typically evolves algorithms as complete, indivisible programs. While this whole-program perspective simplifies the search space, it fundamentally couples the useful local logic to its host program. Consequently, valuable code snippets vanish when the overall program is discarded, making it highly difficult to assess the contribution of individual algorithmic components.To address this, we propose Primitive-Aware Code Evolution (PACE), which decouples local logic from complete programs by representing it as persistent units called Executable Algorithmic Primitives (EAPs). To enable code-level transfer, PACE maintains a dynamic set of EAPs. Algorithm evolution is driven by primitive-aware operators that structurally guarantee the retention and cross-program transfer of these components. To evaluate them effectively, PACE leverages Thompson sampling based on parent-relative performance improvements, guiding primitive selection from the set without requiring extra evaluation datasets. Experiments on four tasks demonstrate that PACE effectively discovers competitive algorithms while structurally preserving valuable algorithmic components.
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。