A Unified Generative Re-ranking Framework with Adaptive Multi-objective Fusion

Abstract

In e-commerce recommendation, effective re-ranking must jointly optimize multiple business objectives such as clicks, add-to-carts, and purchases. Existing methods typically employ either multiple per-objective generators combined with static fusion through handcrafted rules, or adopt non-autoregressive sequence generation with pre-defined objective fusion. Despite their differences, these approaches share a critical limitation: they treat multi-objective signals as statically fused, ignoring the diversity and evolution of user intents in real-time scenarios. To address this gap, we propose MAMGR, a unified generative re-ranking framework that enables end-to-end, sequence-level learning of multiple objectives with dynamic weighting. MAMGR features a Multi-objective Adaptive Module (MAM) that learns personalized objective weights in real time and shares them between the generator and evaluator, and a Dual-channel Context-aware Module (DCM) that jointly models local pairwise interactions and global sequence-level dependencies. Extensive offline and online experiments show that MAMGR consistently outperforms state-of-the-art methods, achieving +0.78% CTR and +1.43% GMV improvements while reducing CPU usage by 23.53% and incurring only +1.12% latency overhead. MAMGR has been deployed in Alipay’s production advertising system, serving hundreds of millions of users daily.