Search papers, labs, and topics across Lattice.
This paper introduces HiLaR, a Hierarchical Latent Reasoning framework designed to enhance LLM-based recommendation systems by constructing temporal-guided hierarchical user preference representations. By aligning these representations with multiple latent reasoning states and optimizing the reasoning trajectory through layer-aware reinforcement, HiLaR effectively improves the modeling of user preferences. Experimental results on four Amazon benchmark datasets demonstrate that HiLaR consistently outperforms existing recommendation methods, highlighting the importance of hierarchical representation learning and process-level optimization in this context.
HiLaR reveals that optimizing user preference modeling through hierarchical latent reasoning can significantly outperform traditional recommendation approaches.
Large Language Models (LLMs) have shown strong potential for recommendation by leveraging their semantic understanding and contextual modeling capabilities. Recent studies further introduce reasoning mechanisms to improve user preference modeling. However, explicit natural-language reasoning incurs substantial inference overhead, whereas existing latent reasoning methods mainly focus on generating or verifying intermediate states, leaving their layer-wise preference roles and contributions insufficiently characterized. We propose HiLaR, a Hierarchical Latent Reasoning framework with layer-aware reinforcement optimization for LLM-based recommendation. HiLaR constructs temporal-guided hierarchical user preference representations, aligns them with multiple LLM latent reasoning states, and organizes the reasoning process from broad preferences to fine-grained current intents. To further optimize the reasoning trajectory, HiLaR combines final recommendation feedback with layer-aware process rewards derived from the marginal target-likelihood gain of each state. Experiments on four Amazon benchmark datasets show that HiLaR generally outperforms strong sequential, generative, and LLM-based recommendation baselines. Ablation and sensitivity analyses further verify the contribution of hierarchical representation learning, latent alignment, and process-level optimization. Our code is available in https://github.com/hupeiyu21/HiLaR.
