超越后继精度：推荐递归自我改进中的状态保留
原标题：Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation
AI 摘要
该论文提出推荐系统递归自我改进（Rec-RSI）中的状态保留问题，指出仅用最新模型评估每轮更新会忽略跨代模型间的互补排序决策。作者定义跨代优势（CGA）来量化这种分布式进展，并用无标签的排名分离统计量预测应保留哪一代模型。在四个数据集和三种序列推荐编码器上，所选模型家族在34/36条轨迹中优于直接后继模型，但五种迁移机制无法稳定复现这些增益。
正文节选
Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation Abstract. Recommendation recursive self-improvement (Rec-RSI) feeds recommender outputs into subsequent training. Evaluating each round solely through its latest model assumes that the successor consolidates the update, although pre- and post-update models may retain complementary ranking decisions. We term this distributed progress and quantify it using cross-generation advantage (CGA), a marginally matc