Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation Article Swipe

MAKE IMPACT

Jiakai Tang , Sunhao Dai , Xu Chen , Wen Chen , Jian Wu , Yuning Jiang · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2503.22675

Sequential Recommendation (SeqRec) aims to predict the next item by capturing sequential patterns from users' historical interactions, playing a crucial role in many real-world recommender systems. However, existing approaches predominantly adopt a direct forward computation paradigm, where the final hidden state of the sequence encoder serves as the user representation. We argue that this inference paradigm, due to its limited computational depth, struggles to model the complex evolving nature of user preferences and lacks a nuanced understanding of long-tail items, leading to suboptimal performance. To address this issue, we propose \textbf{ReaRec}, the first inference-time computing framework for recommender systems, which enhances user representations through implicit multi-step reasoning. Specifically, ReaRec autoregressively feeds the sequence's last hidden state into the sequential recommender while incorporating special reasoning position embeddings to decouple the original item encoding space from the multi-step reasoning space. Moreover, we introduce two lightweight reasoning-based learning methods, Ensemble Reasoning Learning (ERL) and Progressive Reasoning Learning (PRL), to further effectively exploit ReaRec's reasoning potential. Extensive experiments on five public real-world datasets and different SeqRec architectures demonstrate the generality and effectiveness of our proposed ReaRec. Remarkably, post-hoc analyses reveal that ReaRec significantly elevates the performance ceiling of multiple sequential recommendation backbones by approximately 30\%-50\%. Thus, we believe this work can open a new and promising avenue for future research in inference-time computing for sequential recommendation.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2503.22675

PDF

https://arxiv.org/pdf/2503.22675

OA Status

green

OpenAlex ID

https://openalex.org/W4416545260

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4416545260

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2503.22675

Digital Object Identifier

Title

Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-03-28

Full publication date if available

Authors

Jiakai Tang, Sunhao Dai, Xu Chen, Wen Chen, Jian Wu, Yuning Jiang

List of authors in order

Landing page

https://arxiv.org/abs/2503.22675

Publisher landing page

PDF URL

https://arxiv.org/pdf/2503.22675

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2503.22675

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload