OneRec Technical Report

• URL: http://arxiv.org/abs/2506.13695v2
• Date: Thu, 24 Jul 2025 03:28:48 GMT
• Title: OneRec Technical Report
• Authors: Guorui Zhou, Jiaxin Deng, Jinghao Zhang, Kuo Cai, Lejian Ren, Qiang Luo, Qianqian Wang, Qigen Hu, Rui Huang, Shiyao Wang, Weifeng Ding, Wuchao Li, Xinchen Luo, Xingmei Wang, Zexuan Cheng, Zixing Zhang, Bin Zhang, Boxuan Wang, Chaoyi Ma, Chengru Song, Chenhui Wang, Di Wang, Dongxue Meng, Fan Yang, Fangyu Zhang, Feng Jiang, Fuxing Zhang, Gang Wang, Guowang Zhang, Han Li, Hengrui Hu, Hezheng Lin, Hongtao Cheng, Hongyang Cao, Huanjie Wang, Jiaming Huang, Jiapeng Chen, Jiaqiang Liu, Jinghui Jia, Kun Gai, Lantao Hu, Liang Zeng, Liao Yu, Qiang Wang, Qidong Zhou, Shengzhe Wang, Shihui He, Shuang Yang, Shujie Yang, Sui Huang, Tao Wu, Tiantian He, Tingting Gao, Wei Yuan, Xiao Liang, Xiaoxiao Xu, Xugang Liu, Yan Wang, Yi Wang, Yiwu Liu, Yue Song, Yufei Zhang, Yunfan Wu, Yunfeng Zhao, Zhanyu Liu,
• Abstract summary: We propose OneRec, which reshapes the recommendation system through an end-to-end generative approach.<n>Firstly, we have enhanced the computational FLOPs of the current recommendation model by 10 $times$ and have identified the scaling laws for recommendations within certain boundaries.<n> Secondly, reinforcement learning techniques, previously difficult to apply for optimizing recommendations, show significant potential in this framework.
• Score: 65.24343832974165
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recommender systems have been widely used in various large-scale user-oriented platforms for many years. However, compared to the rapid developments in the AI community, recommendation systems have not achieved a breakthrough in recent years. For instance, they still rely on a multi-stage cascaded architecture rather than an end-to-end approach, leading to computational fragmentation and optimization inconsistencies, and hindering the effective application of key breakthrough technologies from the AI community in recommendation scenarios. To address these issues, we propose OneRec, which reshapes the recommendation system through an end-to-end generative approach and achieves promising results. Firstly, we have enhanced the computational FLOPs of the current recommendation model by 10 $\times$ and have identified the scaling laws for recommendations within certain boundaries. Secondly, reinforcement learning techniques, previously difficult to apply for optimizing recommendations, show significant potential in this framework. Lastly, through infrastructure optimizations, we have achieved 23.7% and 28.8% Model FLOPs Utilization (MFU) on flagship GPUs during training and inference, respectively, aligning closely with the LLM community. This architecture significantly reduces communication and storage overhead, resulting in operating expense that is only 10.6% of traditional recommendation pipelines. Deployed in Kuaishou/Kuaishou Lite APP, it handles 25% of total queries per second, enhancing overall App Stay Time by 0.54% and 1.24%, respectively. Additionally, we have observed significant increases in metrics such as 7-day Lifetime, which is a crucial indicator of recommendation experience. We also provide practical lessons and insights derived from developing, optimizing, and maintaining a production-scale recommendation system with significant real-world impact.

Related papers

• RecGPT Technical Report [57.84251629878726]
  We propose RecGPT, a next-generation framework that places user intent at the center of the recommendation pipeline.<n> RecGPT integrates large language models into key stages of user interest mining, item retrieval, and explanation generation.<n>Online experiments demonstrate that RecGPT achieves consistent performance gains across stakeholders.
  arXiv  Detail & Related papers  (2025-07-30T17:55:06Z)
• Improving the Performance of Sequential Recommendation Systems with an Extended Large Language Model [0.0]
  This study proposes to improve LLM-based recommendation systems by replacing Llama2 with Llama3 in the LlamaRec framework.<n>The experimental results show average performance improvements of 38.65%, 8.69%, and 8.19% for the ML-100K, Beauty, and Games datasets, respectively.
  arXiv  Detail & Related papers  (2025-07-26T15:59:25Z)
• $\text{R}^2\text{ec}$: Towards Large Recommender Models with Reasoning [50.291998724376654]
  We propose name, a unified large recommender model with intrinsic reasoning capabilities.<n> RecPO is a corresponding reinforcement learning framework that optimize name both the reasoning and recommendation capabilities simultaneously in a single policy update.<n> Experiments on three datasets with various baselines verify the effectiveness of name, showing relative improvements of 68.67% in Hit@5 and 45.21% in NDCG@20.
  arXiv  Detail & Related papers  (2025-05-22T17:55:43Z)
• eARCO: Efficient Automated Root Cause Analysis with Prompt Optimization [15.299667843493491]
  Root cause analysis (RCA) for incidents in large-scale cloud systems is a complex, knowledge-intensive task.<n>Recent advancements in Large-Language Models (LLMs) have proven to be effective in solving different stages of the incident management lifecycle.<n>We leverage 'PromptWizard', a state-of-the-art prompt optimization technique, to automatically identify the best optimized prompt instruction.
  arXiv  Detail & Related papers  (2025-04-15T08:10:32Z)
• Benchmarking LLMs in Recommendation Tasks: A Comparative Evaluation with Conventional Recommenders [27.273217543282215]
  We introduce RecBench, which evaluates two primary recommendation tasks, i.e., click-through rate prediction (CTR) and sequential recommendation (SeqRec)<n>Our experiments cover up to 17 large models and are conducted across five diverse datasets from fashion, news, video, books, and music domains.<n>Our findings indicate that LLM-based recommenders outperform conventional recommenders, achieving up to a 5% AUC improvement in the CTR scenario and up to a 170% NDCG@10 improvement in the SeqRec scenario.
  arXiv  Detail & Related papers  (2025-03-07T15:05:23Z)
• Scaling New Frontiers: Insights into Large Recommendation Models [74.77410470984168]
  Meta's generative recommendation model HSTU illustrates the scaling laws of recommendation systems by expanding parameters to thousands of billions.<n>We conduct comprehensive ablation studies to explore the origins of these scaling laws.<n>We offer insights into future directions for large recommendation models.
  arXiv  Detail & Related papers  (2024-12-01T07:27:20Z)
• Efficient and Robust Regularized Federated Recommendation [52.24782464815489]
  The recommender system (RSRS) addresses both user preference and privacy concerns. We propose a novel method that incorporates non-uniform gradient descent to improve communication efficiency. RFRecF's superior robustness compared to diverse baselines.
  arXiv  Detail & Related papers  (2024-11-03T12:10:20Z)
• LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoning [40.53821858897774]
  We introduce a novel recommender that synergies Large Language Models (LLMs) and Knowledge Graphs (KGs) to enhance the recommendation and provide interpretable results. Our approach significantly enhances both the effectiveness and interpretability of recommender systems.
  arXiv  Detail & Related papers  (2024-06-22T14:14:03Z)
• DNS-Rec: Data-aware Neural Architecture Search for Recommender Systems [79.76519917171261]
  This paper addresses the computational overhead and resource inefficiency prevalent in Sequential Recommender Systems (SRSs)<n>We introduce an innovative approach combining pruning methods with advanced model designs.<n>Our principal contribution is the development of a Data-aware Neural Architecture Search for Recommender System (DNS-Rec)
  arXiv  Detail & Related papers  (2024-02-01T07:22:52Z)
• Optimizing Audio Recommendations for the Long-Term: A Reinforcement Learning Perspective [11.31980071390936]
  We present a novel podcast recommender system deployed at industrial scale. In deviating from the pervasive industry practice of optimizing machine learning algorithms for short-term proxy metrics, the system substantially improves long-term performance in A/B tests.
  arXiv  Detail & Related papers  (2023-02-07T16:17:25Z)
• PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement [36.95056214316392]
  We propose a novel paradigm, recommender systems with human preferences (or Preference-based Recommender systems) With PrefRec, we can fully exploit the advantages of RL in optimizing long-term goals, while avoiding complex reward engineering.
  arXiv  Detail & Related papers  (2022-12-06T06:21:17Z)
• Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Offline RL [56.20835219296896]
  We study session-based recommendation scenarios where we want to recommend items to users during sequential interactions to improve their long-term utility. We develop a new batch RL algorithm called Short Horizon Policy Improvement (SHPI) that approximates policy-induced distribution shifts across sessions.
  arXiv  Detail & Related papers  (2021-06-01T15:58:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.