# GenRec: A Preference-Oriented Generative Framework for Large-Scale Recommendation

arXiv: https://arxiv.org/abs/2604.14878 · HTML: https://mlsanity.com/paper/2604.14878/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Recommender Systems with Generative Retrieval](https://mlsanity.com/paper/2305.05065/) (2023)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction](https://mlsanity.com/paper/2006.05639/) (2020)
- [Learnable Item Tokenization for Generative Recommendation](https://mlsanity.com/paper/2405.07314/) (2024)
- [From Matching to Generation: A Survey on Generative Information Retrieval](https://mlsanity.com/paper/2404.14851/) (2024)
- [MTGR: Industrial-Scale Generative Recommendation Framework in Meituan](https://mlsanity.com/paper/2505.18654/) (2025)
- [Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations](https://mlsanity.com/paper/2503.02453/) (2025)
- [OneTrans: Unified Feature Interaction and Sequence Modeling with One Transformer in Industrial Recommender](https://mlsanity.com/paper/2510.26104/) (2025)
- [OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System](https://mlsanity.com/paper/2509.18091/) (2025)
- [Enhancing Item Tokenization for Generative Recommendation through Self-Improvement](https://mlsanity.com/paper/2412.17171/) (2024)
- [From IDs to Semantics: A Generative Framework for Cross-Domain Recommendation with Adaptive Semantic Tokenization](https://mlsanity.com/paper/2511.08006/) (2025)
- [Unified Semantic and ID Representation Learning for Deep Recommenders](https://mlsanity.com/paper/2502.16474/) (2025)

## Built on by (most cited first, 5 of 5)

- [UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale](https://mlsanity.com/paper/2606.00422/) (2026)
- [Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models](https://mlsanity.com/paper/2606.19635/) (2026)
- [Learning from Unreachable Rewards: Hint-Conditioned Reinforcement Learning for Generative Recommendation](https://mlsanity.com/paper/2608.11980/) (2026)
- [Difficulty-Aware Semantic-ID Optimization for Generative Recommendation](https://mlsanity.com/paper/2608.20611/) (2026)
- [Adaptive Loss Balancing for Noise-Robust GRPO in Generative Recommendation](https://mlsanity.com/paper/2606.08480/) (2026)

## Abstract (arXiv)

Generative Retrieval (GR) offers a promising paradigm for recommendation through next-token prediction (NTP). However, scaling it to large-scale industrial systems introduces three challenges: (i) within a single request, the identical model inputs may produce inconsistent outputs due to the pagination request mechanism; (ii) the prohibitive cost of encoding long user behavior sequences with multi-token item representations based on semantic IDs, and (iii) aligning the generative policy with nuanced user preference signals. We present GenRec, a preference-oriented generative framework deployed on the JD App that addresses above challenges within a single decoder-only architecture. For training objective, we propose Page-wise NTP task, which supervises over an entire interaction page rather than each interacted item individually, providing denser gradient signal and resolving the one-to-many ambiguity of point-wise training. On the prefilling side, an asymmetric linear Token Merger compresses multi-token Semantic IDs in the prompt while preserving full-resolution decoding, reducing input length by ~2X with negligible accuracy loss. To further align outputs with user satisfaction, we introduce GRPO-SR, a reinforcement learning method that pairs Group Relative Policy Optimization with NLL regularization for training stability, and employs Hybrid Rewards combining a dense reward model with a relevance gate to mitigate reward hacking. In month-long online A/B tests serving production traffic, GenRec achieves 9.5% improvement in click count and 8.7% in transaction count over the existing pipeline.