DeGRe is a dense‑supervised generative reranking framework designed to improve multi‑stage recommender systems by addressing label bias and credit assignment issues. It uses an offline Lookahead Evaluator with beam search to generate dense supervision signals, which are distilled into a lightweight Online Generator that can perform efficient greedy decoding at inference time. Experiments show that DeGRe outperforms baselines on public benchmarks and industrial datasets, and it has been successfully deployed on Taobao Flash Shopping to enhance online recommendations.
By Chaotian Song, Jingyao Zhang, Chenghao Chen, Zisen Sang, Dehai Zhao, Guodong Cao, Boxi Wu, Deng Cai, Jia Jia
The paper introduces Lightweight Ranking Heads (Light Heads), a framework that allows new prediction tasks to be added to large multi-task recommender systems without retraining the backbone model. By using stop‑gradients and stateless daily training, Light Heads isolate new tasks, preventing conflicts with existing ones. Deployed at YouTube scale, the approach cuts multi‑task experimentation cycles from weeks to days, enabling faster A/B testing and deployment of new ranking tasks.
By Sanjay Surendranath Girija, Aniruddh Nath, Li Wei, Yanhao Jiang, Shawn Andrews, Lukasz Heldt, Yi Wu, Aditya Mahajan, Mohit Sharma
arXiv:2602. 07298v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) represent a promising frontier for recommender systems, yet their development has been impeded by the absence of predictable scaling laws, which are crucial for guiding research and optimizing resource allocation.
By Benyu Zhang, Qiang Zhang, Jianpeng Cheng, Hong-You Chen, Qifei Wang, Wei Sun, Shen Li, Jia Li, Jiahao Wu, Qunshu Zhang, Neeraj Bhatia, Xiangjun Fan, Hong Yan
SequenceO1 is an end‑to‑end framework that enables ultra‑long (up to 100K interactions) sequence modeling for recommendation systems. It compresses raw user histories into a fixed‑size sketch using Sketch Attention and then models short‑term and long‑term interests with Target‑to‑History Cross Attention. The system incorporates low‑rank caching, batching, pipeline lift, and a FlashSA kernel to keep training and inference efficient, achieving consistent offline and online performance gains when deployed at full traffic on Douyin.
By Lin Guan, Jia-Qi Yang, Zhishan Zhao, Jiaqi Huang, Hangyu Wang, Longbin Li, Beichuan Zhang, Haonan Jiang, Jinan Ni, Xiangyu Fan, Xiaowen Li, Ziyao Ren, Yuhang Qi, Xiaolong Zhu, Xuanyuan Luo, Qiwei Chen, Yi Cheng, Lele Yu
arXiv:2607. 27475v1 Announce Type: cross Abstract: In modern recommendation systems, retrieval serves as a primary stage responsible for filtering billions of candidate items down to thousands prior to refined ranking.
By Ziwei Li, Shuyao Li, Xufeng Cai, Xue Zou, Yiming Ma, Huiting Lu, Wujie Yan, Zhichen Zhao, Yang Lu, Zhe Wang, Rui Luo, Zhengyu Su, Dan Zhang, Ji Liu
TailSpec-EASE is a lightweight linear recommender that incorporates a relation‑aware spectral knowledge‑graph prior into a local closed‑form reconstruction objective. By adapting the prior strength to item popularity, it provides stronger semantic guidance for long‑tail items. Across four public benchmarks, it achieves a favorable balance of overall accuracy, long‑tail performance, and training cost, improving NDCG@20 by up to 24% over a no‑KG baseline and training in just 37 seconds on CPU compared to thousands of seconds for GPU‑based KGAT and CPU LightGCN.
By Jianru Shen
arXiv:2607. 27577v1 Announce Type: cross Abstract: Heterogeneous recommendation feeds present complex challenges that extend beyond those found in highly homogeneous environments (e.
By Di Bai, Jintao Liu, Zhenwei Tang, Peifan Wu, Nada Al-Thawr, Luoshu Wang
arXiv:2607. 17017v1 Announce Type: cross Abstract: As scalability becomes increasingly important in recommendation modeling, recent architectures have advanced the modeling of two broad sources of ranking signals along separate paths: non-sequence features, including user, item, context, and cross features; and sequence features from user behavior histories.
By Renqin Cai, Dawei Sun, Yuanjun Yao, Zhiyong Wang, Velvin Fu, Maggie Zhuang, Yu Shi, Zhongnan Fang, Xuan Cao, Jing Qian, Rui Li
arXiv:2609.15598v1 Announce Type: cross
Abstract: Generative recommendation has emerged as a promising end-to-end paradigm for personalized recommendation. However, user preferences continuously evol...
By Xinyu Lin, Zhuosong Jiang, Zixiao Suo, Siqin Wang, Hanqing Zeng, Hanchao Yu, Yinglong Xia, Jiang Zhang, Aashu Singh, Fei Liu, Wenjie Wang, Fuli Feng, Yang Song, Qifan Wang, Tat-Seng Chua
arXiv:2607. 12281v1 Announce Type: cross Abstract: Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet they inherit a design premise misaligned with the task: generative models rely on per-token autoregressive prediction, which justifies maintaining large intermediate tensors that scale with sequence length.
By Siqi Wang, Xianjie Chen, Shaofeng Deng, Albert Chen, Romil Shah, Jiawei Huang, Zhaoqin Wang, Zhang Zhang, Yiqun Liu, Meilei Jiang, Anish Dubey, Moyan Mei, Tongxin Wang, Nathan Berrebbi, Misael Manjarres, Armand Sauzay, Shardul Kothapalli, Aryaman Vinchhi, Kevin Johnstone, Juheon Lee, Gufan Yin, Ziheng Huang, Justin Lin, Mert Terzihan, Yilin Qi, Cynthia Yang, Colin Peppler, Qi Ding, Ruohan Sun, Ge Song, Litao Deng, Parichay Kapoor, Matt Ma, Huihui Cheng, Jiyuan Zhang, Yanli Zhao, Yiping Han, Fangqiu Han, Ning Yao, Arun Singh, Jordan Edwards, Zhengyu Su, Abhishek Kumar, Guangdeng Liao, Ankit Asthana
arXiv:2606. 01111v1 Announce Type: new Abstract: Modern industrial recommender systems rely on thousands of heterogeneous features -- ranging from low-dimensional scalars (e.
By Yihong Huang, Chen Chu, Fei Chen, Yu Lin, Ruiduan Li, Zhihao Li
The paper presents a method for fine‑tuning a large language model (LLM) recommender to generate personalized, non‑harmful explanations for its recommendations. By training two LLM‑judge reward models and using constrained GRPO, the authors achieve a significant increase in the PASS rate for all three criteria, from 0.649 to 0.956 on their own judges and from 0.677 to 0.931 on an independent judge. The fine‑tuned model maintains its original recommendation performance, demonstrating that LLM‑based recommenders can be adapted to complex tasks without loss of effectiveness.
By Jiashu He, Emma Yanyang Kong, JJ Tan, David Fagnan