OxygenREC: An Instruction-Following Generative Framework for E-commerce Recommendation
Xuegang Hao, Ming Zhang, Alex Li, Xiangyu Qian, Zhi Ma, Yanlong Zang, Shijie Yang, Zhongxuan Han, Xiaolong Ma, Jinguang Liu, Zhen Li, Zhida Jiang, Shusheng Wang, Ning Tang, Yanchen Qiao, Chenxiang Yang, Chen Sun, Jincheng Yuan, Chunhua Peng, Heng Hu, Peijun Yang, Baopeng Yuan

TL;DR
OxygenREC is an industrial recommendation framework that combines fast and slow reasoning processes, semantic alignment, and scalable multi-scenario adaptation to improve recommendation accuracy and efficiency in real-world settings.
Contribution
It introduces a novel Fast-Slow Thinking architecture, semantic alignment with instruction-guided retrieval, and a scalable multi-scenario training paradigm for recommendation systems.
Findings
Achieves deep reasoning with low latency in recommendation tasks.
Effectively filters intent-relevant behaviors using semantic alignment.
Supports multi-scenario deployment with a train-once-deploy-everywhere approach.
Abstract
Traditional recommendation systems suffer from inconsistency in multi-stage optimization objectives. Generative Recommendation (GR) mitigates them through an end-to-end framework; however, existing methods still rely on matching mechanisms based on inductive patterns. Although responsive, they lack the ability to uncover complex user intents that require deductive reasoning based on world knowledge. Meanwhile, LLMs show strong deep reasoning capabilities, but their latency and computational costs remain challenging for industrial applications. More critically, there are performance bottlenecks in multi-scenario scalability: as shown in Figure 1, existing solutions require independent training and deployment for each scenario, leading to low resource utilization and high maintenance costs-a challenge unaddressed in GR literature. To address these, we present OxygenREC, an industrial…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRecommender Systems and Techniques · Explainable Artificial Intelligence (XAI) · Advanced Bandit Algorithms Research
