Reasoning over Semantic IDs Enhances Generative Recommendation

• URL: http://arxiv.org/abs/2603.23183v1
• Date: Tue, 24 Mar 2026 13:31:48 GMT
• Title: Reasoning over Semantic IDs Enhances Generative Recommendation
• Abstract summary: We propose a two-stage framework that elicits reasoning over SIDs by strengthening SID--language alignment.<n> SIDReasoner further improves recommendation reasoning through outcome-driven reinforced optimization.<n>Our experiments on three real-world datasets demonstrate the effectiveness of our reasoning-augmented SID-based generative recommendation.
• Score: 56.83043583765322
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in generative recommendation have leveraged pretrained LLMs by formulating sequential recommendation as autoregressive generation over a unified token space comprising language tokens and itemic identifiers, where each item is represented by a compact sequence of discrete tokens, namely Semantic IDs (SIDs). This SID-based formulation enables efficient decoding over large-scale item corpora and provides a natural interface for LLM-based recommenders to leverage rich world knowledge. Meanwhile, breakthroughs in LLM reasoning motivate reasoning-enhanced recommendation, yet effective reasoning over SIDs remains underexplored and challenging. Itemic tokens are not natively meaningful to LLMs; moreover, recommendation-oriented SID reasoning is hard to evaluate, making high-quality supervision scarce. To address these challenges, we propose SIDReasoner, a two-stage framework that elicits reasoning over SIDs by strengthening SID--language alignment to unlock transferable LLM reasoning, rather than relying on large amounts of recommendation-specific reasoning traces. Concretely, SIDReasoner first enhances SID-language alignment via multi-task training on an enriched SID-centered corpus synthesized by a stronger teacher model, grounding itemic tokens in diverse semantic and behavioral contexts. Building on this enhanced alignment, SIDReasoner further improves recommendation reasoning through outcome-driven reinforced optimization, which guides the model toward effective reasoning trajectories without requiring explicit reasoning annotations. Extensive experiments on three real-world datasets demonstrate the effectiveness of our reasoning-augmented SID-based generative recommendation. Beyond accuracy, the results highlight the broader potential of large reasoning models for generative recommendation, including improved interpretability and cross-domain generalization.

Related papers

• SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation [43.98709365191658]
  Generative recommendation treats next-item prediction as autoregressive item-identifier generation.<n>Recent work augments this paradigm with reasoning traces and optimize them via reinforcement learning with verifiable rewards.<n>In large-catalog recommendation, exact-match feedback on the generated SID only reports whether the final item is correct.
  arXiv  Detail & Related papers  (2026-05-17T20:53:08Z)
• Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs [17.944727019161878]
  ReSID is a principled, SID framework that recommend learning from the perspective of information preservation and sequential predictability.<n>It consistently outperforms strong sequential and SID-based generative baselines by an average of over 10%, while reducing tokenization cost by up to 122x.
  arXiv  Detail & Related papers  (2026-02-02T17:00:04Z)
• S$^2$GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation [15.69884243417431]
  Generative Recommendation (GR) has emerged as a transformative paradigm with its end-to-end generation advantages.<n>Existing GR methods primarily focus on direct Semantic ID (SID) generation from interaction sequences.<n>We propose stepwise semantic-guided reasoning in latent space (S$2$GR), a novel reasoning enhanced GR framework.
  arXiv  Detail & Related papers  (2026-01-26T16:40:37Z)
• Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers [51.64398574262054]
  This paper introduces Term IDs (TIDs), defined as a set of semantically rich and standardized textual keywords, to serve as robust item identifiers.<n>We propose GRLM, a novel framework centered on TIDs, to convert item's metadata into standardized TIDs and utilize Integrative Instruction Fine-tuning to collaboratively optimize term internalization and sequential recommendation.
  arXiv  Detail & Related papers  (2026-01-11T07:53:20Z)
• Generative Reasoning Recommendation via LLMs [48.45009951684554]
  Large language models (LLMs) face fundamental challenges in functioning as generative reasoning recommendation models (GRRMs)<n>This work explores how to build GRRMs by adapting pre-trained LLMs, which achieves a unified understanding-reasoning-prediction manner for recommendation tasks.<n>We propose GREAM, an end-to-end framework that integrates three components: Collaborative-Semantic Alignment, Reasoning Curriculum Activation, and Sparse-Regularized Group Policy Optimization.
  arXiv  Detail & Related papers  (2025-10-23T17:59:31Z)
• EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration [60.47645731801866]
  Large language models (LLMs) are increasingly leveraged as foundational backbones in advanced recommender systems.<n>LLMs are pre-trained linguistic semantics but learn collaborative semantics from scratch via the llm-Backbone.<n>We propose EAGER-LLM, a decoder-only generative recommendation framework that integrates endogenous and endogenous behavioral and semantic information in a non-intrusive manner.
  arXiv  Detail & Related papers  (2025-02-20T17:01:57Z)
• Towards Scalable Semantic Representation for Recommendation [65.06144407288127]
  Mixture-of-Codes is proposed to construct semantic IDs based on large language models (LLMs) Our method achieves superior discriminability and dimension robustness scalability, leading to the best scale-up performance in recommendations.
  arXiv  Detail & Related papers  (2024-10-12T15:10:56Z)
• Learnable Item Tokenization for Generative Recommendation [113.80559032128065]
  We propose LETTER (a LEarnable Tokenizer for generaTivE Recommendation), which integrates hierarchical semantics, collaborative signals, and code assignment diversity.<n> LETTER incorporates Residual Quantized VAE for semantic regularization, a contrastive alignment loss for collaborative regularization, and a diversity loss to mitigate code assignment bias.
  arXiv  Detail & Related papers  (2024-05-12T15:49:38Z)

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.