About this paper
A unified decoder-only policy guided by reward-model-based reinforcement learning generates recommendation exposure slates end-to-end, improving business metrics and reducing reranking and mix-ranking latency in a large-scale system.
Industrial recommender systems allocate substantial computation to pointwise candidate scoring, yet separate reranking and mix-ranking stages still assemble the final exposure slate using hand-crafted rules and specialized low-capacity models. Mix-ranking combines product cards, short videos, livestreams, and advertising cards supplied by distinct upstream business channels. Although these rules and models encode valuable domain knowledge, they are inherently limited in leveraging additional data and computation. They constrain the combinatorial space of candidate slates and determine objective trade-offs through manual tuning. To enable scalable and effective slate generation, we…
decoder-only policyOneTrans-GSROneTrans backbonereward modelreinforcement learningslate generationend-to-end generationrerankingmix-rankingexposure slate
- Upvotes
- 32
- Authors
- 16
- Published
- Nov 3, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
OneTrans-GSR: A Generative Slate Ranking Paradigm Unifying Reranking and Mix-Ranking with One Autoregressive Transformer was first seen on Hugging Face · Daily papers on Nov 10, 2026. Since then it has appeared in 4 checks on 1 different day. Its best position was #7 of 30, reached on Nov 10, 07:28 UTC. It dropped off the list after Nov 10, 13:28 UTC.