Evo-Rec is proposed, a three-stage framework for learning better reasoning and further enhancing it through reinforcement learning that consistently outperforms discriminative, generative, and reasoning-enhanced recommenders across all evaluation metrics.
Abstract
Generative recommendation reformulates item retrieval as sequence generation, allowing a unified model to directly generate the next item from a user's interaction history. Semantic IDs further make this paradigm effective and scalable by representing each item as discrete codes, enabling knowledge sharing among semantically related items. Recent studies introduce explicit reasoning before Semantic-ID generation, helping models summarize user interests and infer possible preference transitions. However, reasoning is not inherently beneficial: Inaccurate or uninformative reasoning may mislead subsequent item generation and ultimately degrade recommendation performance. This raises a central challenge: how can a recommender select and learn effective reasoning traces and progressively evolve toward better reasoning from its own generations? In this work, we propose Evo-Rec, a three-stage framework for learning better reasoning and further enhancing it through reinforcement learning. First, we align Semantic IDs with their textual and behavioral contexts, enabling the model to understand and generate item identifiers. Second, we sample multiple candidate reasoning traces and retain those that improve the prediction of the ground-truth item, providing a stronger reasoning initialization through supervised fine-tuning. Third, we further optimize the reasoning policy through reinforcement learning with catalog-constrained item generation and ranking-aware recommendation feedback. Experiments on three Amazon Review benchmarks show that Evo-Rec consistently outperforms discriminative, generative, and reasoning-enhanced recommenders across all evaluation metrics. These results demonstrate the effectiveness of our framework in learning better reasoning for SID-based generative recommendation.
This work addresses the credit-assignment gap in SID recommendation with retrieval-grounded query attribution, and reveals the potential of interest-conditioned SID decoding: selecting the target-relevant query among generated interests improves both recall and ranking.
Meng-Dan Zhu, Yu-Fan Zhao, Yao Zhao et al.· 0 citations
This work proposes Hint-Conditioned Generative Recommendation (HCGRec), a semantic-ID generative recommendation framework that recovers learning signal for such hard training instances and introduces hint-aware credit decomposition, using supervised learning to preserve item-semantic and prefix-structure alignment for...
Kang-Ning Zhang, Hao Fang, Xukun Luo et al.· ACM International Conference...· 0 citations
SelfDR distills an LLM's own reasoning-enhanced predictions to produce recommendations directly, improving recommendation effectiveness while maintaining inference efficiency, and validate the effectiveness, rationality, and efficiency of SelfDR.
Chumeng Jiang, Jiayin Wang, Xin-Jie Lin et al.· 1 citation
It is found that introducing explicit descriptive reasoning traces reduces traditional offline recommendation effectiveness under standard SFT and RL training, even though natural language titles produce substantially more grounded and interpretable traces.
G. Penha, Juan Elenter, Claudia Hauff et al.· 0 citations
Semantic ID (SID) generative recommendation predicts the next item by generating a short tuple of discrete tokens. Recent masked-diffusion methods improve this process through bidirectional context and flexible decoding, yet recommendation ultimately requires selecting among complete catalog items. At each denoising st...
Tuan-Binh Tran, T. Nguyen, Quoc Viet Hung Nguyen et al.· 0 citations
A series of models are explored that connect item Semantic IDs with natural language in a unified representation space and seek to unlock the potential of natural-language chain-of-thought (CoT) reasoning for recommendation, including OneReason.