发表机构
City University of Hong Kong; Kuaishou Technology; Xi’an Jiaotong University（香港城市大学; 快手科技; 西安交通大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
EvoSkillRec提出技能基因组进化框架，通过受约束技能空间与开放式代码空间协同进化，实现推荐架构的累积式发现与复用，并在多任务实验中验证其有效性。
AI 中文摘要
现代推荐系统的进步不仅依赖于数据规模和参数规模的扩大，还通过架构编码任务特定的归纳偏置，包括用于点击率（CTR）预测的稀疏特征交互、用于序列推荐的时序注意力以及用于多任务学习的专家路由。然而，这些偏置通常由人类专家设计或在预定义算子空间内搜索得到。尽管近期基于大语言模型（LLM）的代码进化扩展了这一空间，但无约束的编辑往往产生无效或低效的架构，未能充分利用已有的架构设计知识，并且无法保留成功的创新以供复用。我们提出EvoSkillRec，一个用于累积式推荐架构进化的促进与复用框架。它首先将推荐系统分解为原子可执行技能，并将架构表示为带类型的技能基因组，每个技能配备输入-输出类型、语义注释和实现代码。然后，我们通过两个耦合空间进化不同任务的模型：一个受约束的技能空间，用于变异、重组、特化和复用经过验证的技能；一个开放式的代码空间，其中LLM规划器和合成器利用先前的进化轨迹和累积经验发明新的技能模块。一个自动研究控制器评估候选方案、诊断失败、检索相关技能、将验证过的创新提升到技能库中，并自适应地在两个空间之间分配提案预算。在CTR预测、多任务学习和多领域学习上的大量实验，包括生成式排序模型中预测质量与模型FLOPs利用率的资源受限协同优化，一致地证明了我们提出的EvoSkillRec的有效性。
英文摘要
Modern recommender systems advance not only by scaling data and parameters, but also by encoding task-specific inductive biases through architecture, including sparse feature interactions for click-through rate (CTR) prediction, temporal attention for sequential recommendation, and expert routing for multi-task learning. However, these biases are typically human expert designed or searched within predefined operator spaces. Although Recent LLM-driven code evolution expands this space, unconstrained edits often produce invalid or ineffective architectures, underuse established architecture design knowledge, and fail to preserve successful innovations for reuse. We introduce EvoSkillRec, a promotion-and-reuse framework for cumulative recommender architecture evolution. It first decomposes recommenders into atomic executable skills and represents architectures as typed skill genomes, with each skill equipped with input--output types, semantic annotations, and implementation code. We then evolve models with different tasks through two coupled spaces: a constrained skill--space that mutates, recombines, specializes, and reuses validated skills, and an open-ended code--space in which LLM planners and synthesizers invent new skill modules using prior evolution traces and accumulated experience. An autoresearch controller evaluates candidates, diagnoses failures, retrieves relevant skills, promotes validated innovations into the skill library, and adaptively allocates the proposal budget between the two spaces. Extensive experiments on CTR prediction, multi-task learning, and multi-domain learning, including resource-constrained co-optimization of predictive quality and model FLOPs utilization in generative ranking models, consistently demonstrate the effectiveness of our proposed EvoSkillRec.
