Intent-Guided Reasoning for Sequential Recommendation

TL;DR

This paper introduces IGR-SR, a novel intent-guided reasoning framework for sequential recommendation that enhances robustness and understanding by explicitly modeling user intents, outperforming existing methods especially under noisy conditions.

Contribution

The paper proposes a new framework with three components that explicitly extract and utilize high-level user intents to improve recommendation accuracy and robustness.

Findings

IGR-SR achieves an average 7.13% improvement over baselines.

Under 20% behavioral noise, IGR-SR degrades only 10.4%.

Demonstrates robustness and effectiveness of intent-guided reasoning.

Abstract

Sequential recommendation systems aim to capture users' evolving preferences from their interaction histories. Recent reasoningenhanced methods have shown promise by introducing deliberate, chain-of-thought-like processes with intermediate reasoning steps. However, these methods rely solely on the next target item as supervision, leading to two critical issues: (1) reasoning instability--the process becomes overly sensitive to recent behaviors and spurious interactions like accidental clicks, and (2) surface-level reasoning--the model memorizes item-to-item transitions rather than understanding intrinsic behavior patterns. To address these challenges, we propose IGR-SR, an Intent-Guided Reasoning framework for Sequential Recommendation that anchors the reasoning process to explicitly extracted high-level intents. Our framework comprises three key components: (1) a Latent Intent Distiller (LID) that efficiently extracts multi-faceted intents using a frozen encoder with learnable tokens, (2) an Intent-aware Deliberative Reasoner (IDR) that decouples reasoning into intent deliberation and decision-making via a dual-attention architecture, and (3) an Intent Consistency Regularization (ICR) that ensures robustness by enforcing consistent representations across different intent views. Extensive experiments on three public datasets demonstrate that IGR-SR achieves an average 7.13% improvement over state-of-the-art baselines. Critically, under 20% behavioral noise, IGR-SR degrades only 10.4% compared to 16.2% and 18.6% for competing methods, validating the effectiveness and robustness of intent-guided reasoning.