OxygenREC-v2: Internalizing Discrimination into Generative Recommendation

• URL: http://arxiv.org/abs/2607.24255v1
• Date: Mon, 27 Jul 2026 10:45:48 GMT
• Title: OxygenREC-v2: Internalizing Discrimination into Generative Recommendation
• Abstract summary: We propose OxygenREC-v2, a generative recommender that Internalizes Discrimination into Generative Recommendation (IDGR)<n>Rather than adding a separate discriminative objective, OxygenREC-v2 uses logged behavior to condition generation and supervise training.
• Score: 10.320822317650732
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative recommendation unifies retrieval and ranking within a single model by autoregressively decoding semantic identifier (SID) sequences. Yet reliably incorporating behavior signals from clicks, cart additions, and orders remains challenging. Existing approaches either jointly optimize generative and discriminative objectives, requiring delicate trade-offs, or use a separate ranker as a post-hoc reinforcement-learning reward, risking out-of-distribution scoring and reward misalignment. We propose OxygenREC-v2, a generative recommender that Internalizes Discrimination into Generative Recommendation (IDGR). Rather than adding a separate discriminative objective, OxygenREC-v2 uses logged behavior to condition generation and supervise training. During pre-training, a behavior instruction conditions generation on the target behavior. During post-training, future interaction behaviors are exploited as privileged knowledge in our entropy-aware trajectory optimization self-distillation framework, enabling reward-model-free policy optimization. Throughout both training stages, OxygenREC-v2 maintains a single unified backbone. We implement OxygenREC-v2 as a 3B-parameter, 1B-activated MoE and deploy it on JD.com's large-scale e-commerce platform. Across multiple online A/B tests, OxygenREC-v2 improves user click-through conversion rate (UCTCVR) by 1.6--4.4% and GMV by 2.8--6.8% over OxygenREC-v1.

Related papers

• CurateEvo: Data-Curation Evolving for Agentic Post-Training [53.68149869349268]
  We propose CurateEvo, a failure-driven dynamic evolution framework for agentic post-training data curation.<n>CurateEvo represents the curation strategy as executable code and iteratively rewrites it using failed trajectories from a held-out development set.<n>At each epoch, the evolved strategy transforms a fixed raw corpus into supervised fine-tuning data, reinforcement learning data, and an inference-time memory bank.
  arXiv  Detail & Related papers  (2026-07-07T11:07:00Z)
• INFUSER: Influence-Guided Self-Evolution Improves Reasoning [54.101135873140066]
  We introduce an iterative co-training framework with two co-evolving roles.<n>A solver is trained with standard correctness rewards against the generator-provided answers.<n>An 8B INF co-evolving generator outperforms a frozen 32B thinking generator on math and coding.
  arXiv  Detail & Related papers  (2026-06-08T05:40:36Z)
• Discrimination Is Generation: Unifying Ranking and Retrieval from a Tokenizer Perspective [14.332200648147863]
  We propose DIG (textbfDiscrimination textbfIs textbfGeneration), which embeds the tokenizer inside a discriminative ranking model for end-to-end training.<n> Experiments on three public benchmarks and two industrial datasets demonstrate that DIG simultaneously improves ranking, retrieval, and unified retrieval-ranking quality.
  arXiv  Detail & Related papers  (2026-05-14T13:59:29Z)
• AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation [59.964989458924585]
  AdaExplore is an agent framework that enables self-improvement via accumulated execution feedback for performance-critical kernel code generation.<n>In the adaptation stage, the agent synthesizes tasks and converts recurring failures into a reusable memory of validity rules.<n>In the search stage, the agent organizes candidate kernels as a tree and alternates between small local refinements and larger structural regeneration.
  arXiv  Detail & Related papers  (2026-04-17T18:25:03Z)
• Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision [50.61441331643804]
  Reinforcement learning (RLVR) relies on binary rewards, which are broadly applicable and powerful, but provide only sparse supervision during training.<n>Distillation provides dense token-level supervision, typically obtained from an external teacher or using high-quality demonstrations.<n>We propose Self-Distillation Zero (SD-Zero), a method that is substantially more training sample-efficient than RL and does not require an external teacher or high-quality demonstrations.
  arXiv  Detail & Related papers  (2026-04-13T19:46:55Z)
• Self-Distilled RLVR [57.37526213765131]
  We show that learning signals solely derived from the privileged teacher result in severe information leakage and unstable long-term training.<n>We propose textbfRLSD (textbfRLVR with textbfSelf-textbfDistillation)<n>This enables RLSD to simultaneously harness the strengths of both RLVR and OPSD, achieving a higher convergence ceiling and superior training stability.
  arXiv  Detail & Related papers  (2026-04-03T15:50:07Z)
• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• EmoLoom-2B: Fast Base-Model Screening for Emotion Classification and VAD with Lexicon-Weak Supervision and KV-Off Evaluation [14.702916401734916]
  EmoLoom-2B turns small language models under 2B parameters into fast screening candidates for emotion classification and Valence-Arousal-Dominance prediction.<n>To ensure protocol-faithful and fair evaluation, we unify data loading, training, and inference under a single input-output contract.
  arXiv  Detail & Related papers  (2026-01-03T08:25:58Z)
• Binary Kernel Logistic Regression: a sparsity-inducing formulation and a convergent decomposition training algorithm [0.5680416078423551]
  Kernel logistic regression (KLR) is a widely used supervised learning method for binary and multi-class classification.<n>Previous attempts to deal with sparsity in KLR include a method referred to as the Vector Import Machine (IVM)<n>We propose an extension of the training formulation proposed by Keerthi et al., which is able to induce sparsity in the trained model.
  arXiv  Detail & Related papers  (2025-12-22T14:40:30Z)
• MiniOneRec: An Open-Source Framework for Scaling Generative Recommendation [44.05859062614669]
  MiniOneRec is the first fully open-source generative recommendation framework.<n>It provides an end-to-end workflow spanning SID construction, supervised fine-tuning, and recommendation-oriented reinforcement learning.<n>Our experiments reveal a consistent downward trend in both training and evaluation losses with increasing model size.
  arXiv  Detail & Related papers  (2025-10-28T13:58:36Z)
• Forward and inverse reinforcement learning sharing network weights and hyperparameters [3.705785916791345]
  ERIL combines forward and inverse reinforcement learning (RL) under the framework of an entropy-regularized Markov decision process. A forward RL step minimizes the reverse KL estimated by the inverse RL step. We show that minimizing the reverse KL divergence is equivalent to finding an optimal policy.
  arXiv  Detail & Related papers  (2020-08-17T13:12:44Z)

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.