S$^2$GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation

TL;DR

This paper introduces S$^2$GR, a novel framework for generative recommendation that enhances reasoning capabilities through stepwise semantic-guided reasoning in latent space, improving performance and interpretability.

Contribution

The paper proposes a new reasoning-enhanced generative recommendation framework with stepwise semantic guidance, codebook optimization, and supervised reasoning tokens, addressing limitations of existing methods.

Findings

S$^2$GR outperforms existing methods in recommendation quality.

Online A/B tests show significant improvements on a large-scale platform.

Semantic-guided reasoning enhances interpretability and reasoning depth.

Abstract

Generative Recommendation (GR) has emerged as a transformative paradigm with its end-to-end generation advantages. However, existing GR methods primarily focus on direct Semantic ID (SID) generation from interaction sequences, failing to activate deeper reasoning capabilities analogous to those in large language models and thus limiting performance potential. We identify two critical limitations in current reasoning-enhanced GR approaches: (1) Strict sequential separation between reasoning and generation steps creates imbalanced computational focus across hierarchical SID codes, degrading quality for SID codes; (2) Generated reasoning vectors lack interpretable semantics, while reasoning paths suffer from unverifiable supervision. In this paper, we propose stepwise semantic-guided reasoning in latent space (S$^2$GR), a novel reasoning enhanced GR framework. First, we establish a robust semantic foundation via codebook optimization, integrating item co-occurrence relationship to capture behavioral patterns, and load balancing and uniformity objectives that maximize codebook utilization while reinforcing coarse-to-fine semantic hierarchies. Our core innovation introduces the stepwise reasoning mechanism inserting thinking tokens before each SID generation step, where each token explicitly represents coarse-grained semantics supervised via contrastive learning against ground-truth codebook cluster distributions ensuring physically grounded reasoning paths and balanced computational focus across all SID codes. Extensive experiments demonstrate the superiority of S$^2$GR, and online A/B test confirms efficacy on large-scale industrial short video platform.