# LARES: Latent Reasoning for Sequential Recommendation

arXiv: https://arxiv.org/abs/2505.16865 · HTML: https://mlsanity.com/paper/2505.16865/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2025.

## Built on by (most cited first, 12 of 12)

- [The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook](https://mlsanity.com/paper/2604.02029/) (2026)
- [OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System](https://mlsanity.com/paper/2509.18091/) (2025)
- [S2GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation](https://mlsanity.com/paper/2601.18664/) (2026)
- [Navigating Through Paper Flood: Advancing LLM-based Paper Evaluation through Domain-Aware Retrieval and Latent Reasoning](https://mlsanity.com/paper/2508.05129/) (2025)
- [MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedback](https://mlsanity.com/paper/2510.22888/) (2025)
- [DTRec: Learning Dynamic Reasoning Trajectories for Sequential Recommendation](https://mlsanity.com/paper/2512.14036/) (2025)
- [BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models](https://mlsanity.com/paper/2601.22925/) (2026)
- [LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation](https://mlsanity.com/paper/2605.10207/) (2026)
- [Intuition-Guided Latent Reasoning for LLM-Based Recommendation](https://mlsanity.com/paper/2606.27684/) (2026)
- [LaRec: Unleashing LLM-based Latent Reasoning for Generative Recommendation](https://mlsanity.com/paper/2607.24617/) (2026)
- [Hierarchical Latent Reasoning for LLM-based Recommendation](https://mlsanity.com/paper/2607.27760/) (2026)
- [The Disconnect Between Better Descriptive Reasoning Trace Quality and Recommendation Effectiveness](https://mlsanity.com/paper/2608.23154/) (2026)

## Abstract (arXiv)

Sequential recommender systems have become increasingly important in real-world applications that model user behavior sequences to predict their preferences. However, existing sequential recommendation methods predominantly rely on non-reasoning paradigms, which may limit the model's computational capacity and result in suboptimal recommendation performance. To address these limitations, we present LARES, a novel and scalable LAtent REasoning framework for Sequential recommendation that enhances model's representation capabilities through increasing the computation density of parameters by depth-recurrent latent reasoning. Our proposed approach employs a recurrent architecture that allows flexible expansion of reasoning depth without increasing parameter complexity, thereby effectively capturing dynamic and intricate user interest patterns. A key difference of LARES lies in refining all input tokens at each implicit reasoning step to improve the computation utilization. To fully unlock the model's reasoning potential, we design a two-phase training strategy: (1) Self-supervised pre-training (SPT) with dual alignment objectives; (2) Reinforcement post-training (RPT). During the first phase, we introduce trajectory-level alignment and step-level alignment objectives, which enable the model to learn recommendation-oriented latent reasoning patterns without requiring supplementary annotated data. The subsequent phase utilizes reinforcement learning (RL) to harness the model's exploratory ability, further refining its reasoning capabilities. Comprehensive experiments on real-world benchmarks demonstrate our framework's superior performance. Notably, LARES exhibits seamless compatibility with existing advanced models, further improving their recommendation performance. Our code is available at https://anonymous.4open.science/r/LARES-E458/.