Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

R3-REC: Reasoning-Driven Recommendation via Retrieval-Augmented LLMs over Multi-Granular Interest Signals

Yuchen Miao, Mingxuan Cui, Yitong Zhu, Yu Wang, Siyang Xu

Abstract

This paper addresses two persistent challenges in sequential recommendation: (i) evidence insufficiency-cold-start sparsity together with noisy, length-varying item texts; and (ii) opaque modeling of dynamic, multi-faceted intents across long/short horizons. We propose R3-REC (Reasoning-Retrieval-Recommendation), a prompt-centric, retrieval-augmented framework that unifies Multi-level User Intent Reasoning, Item Semantic Extraction, Long-Short Interest Polarity Mining, Similar User Collaborative Enhancement, and Reasoning-based Interest Matching and Scoring. Across ML-1M, Games, and Bundle, R3-REC consistently surpasses strong neural and LLM baselines, yielding improvements up to +10.2% (HR@1) and +6.4% (HR@5) with manageable end-to-end latency. Ablations corroborate complementary gains of all modules.

R3-REC: Reasoning-Driven Recommendation via Retrieval-Augmented LLMs over Multi-Granular Interest Signals

Abstract

This paper addresses two persistent challenges in sequential recommendation: (i) evidence insufficiency-cold-start sparsity together with noisy, length-varying item texts; and (ii) opaque modeling of dynamic, multi-faceted intents across long/short horizons. We propose R3-REC (Reasoning-Retrieval-Recommendation), a prompt-centric, retrieval-augmented framework that unifies Multi-level User Intent Reasoning, Item Semantic Extraction, Long-Short Interest Polarity Mining, Similar User Collaborative Enhancement, and Reasoning-based Interest Matching and Scoring. Across ML-1M, Games, and Bundle, R3-REC consistently surpasses strong neural and LLM baselines, yielding improvements up to +10.2% (HR@1) and +6.4% (HR@5) with manageable end-to-end latency. Ablations corroborate complementary gains of all modules.
Paper Structure (15 sections, 6 equations, 4 figures, 2 tables)

This paper contains 15 sections, 6 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction and Related Work
  2. METHODOLOGY
  3. Hierarchical Intent and Temporal Polarity Modeling
  4. Multi-level Recent Intent
  5. Long-Short Interest Polarity
  6. Item Semantic Extraction
  7. Similar User Collaborative Enhancement
  8. Reasoning-based Interest Matching
  9. EXPERIMENTS AND RESULTS
  10. Experiment settings
  11. Overall Performance Comparison
  12. Ablation Studies
  13. Hyperparameter Sensitivity
  14. Efficiency and Cost Analysis
  15. CONCLUSION

Figures (4)

  • Figure 1: Challenges and solution: (i) evidence insufficiency (cold-start + noisy item texts), (ii) opaque modeling of long/short-horizon intents.
  • Figure 2: Methodology Overview of $R^3$-REC. The pipeline consists of four stages: (1) Raw Data Processing handles user session streams; (2) Multi-granularity Enhancement distills item semantics via LLMs and models hierarchical user interests (including intent reasoning and long-short term polarity mining); (3) Prompt-guided Assembly Reasoning constructs a comprehensive prompt context by inserting retrieved similar users, inferred intents, and candidates; (4) Context-aware Recommendation employs an LLM to perform feature analysis, generating both ranking scores and interpretative reasoning.
  • Figure 3: Ablation on R3-REC (HR@1 / HR@5 / NDCG@5). Lower bars on variants indicate performance drops relative to the full model.
  • Figure 4: Hyperparameter sensitivity under two factorizations.