Industrial recommender systems use cascaded stages with different candidate spaces, data distributions, and latency constraints. Independently optimizing their multi-task fusion (MTF) modules can cause cross-stage preference inconsistency, while existing cross-stage methods mainly transfer supervision to upstream scoring models and leave fusion modules jointly unoptimized. We propose UniRec, a Unified Cross-stage Recommendation Fusion framework that jointly optimizes pre-ranking and ranking fusion agents. UniRec employs a coupled dual-agent architecture with partially shared embeddings and stage-specific fusion functions. It further introduces Dual-Axis Preference Optimization to combine stage-local preferences with downstream-to-upstream preference transfer. Attribute Group-Relative Regularization (AGRR) mitigates reward-induced distribution drift by normalizing preference advantages within attribute groups. To improve efficiency, Compact Pairwise Preference Aggregation (CPPA) reduces the objective-dependent pairwise complexity, while Confidence-Aware Pair Pruning (CAPP) further reduces the evaluated pair space. Extensive offline and online experiments on a production short-video system demonstrate consistent gains over single-stage fusion and cross-stage coordination baselines. In a nine-week online A/B test, UniRec improves total watch time by $0.675\%$ and app usage time by $0.616\%$, and has been fully deployed in production.

翻译：暂无翻译