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

arXiv: https://arxiv.org/abs/2603.13730 · HTML: https://mlsanity.com/paper/2603.13730/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 14 Mar 2026.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)
- Retrieval-augmented generation / [RAG for recommendation](https://mlsanity.com/rag/rag-for-recommendation/)

## Builds on (most cited first, 20 of 20)

- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [Session-based Recommendation with Graph Neural Networks](https://mlsanity.com/paper/1811.00855/) (2018)
- [Neural Attentive Session-based Recommendation](https://mlsanity.com/paper/1711.04725/) (2017)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [Multi-Interest Network with Dynamic Routing for Recommendation at Tmall](https://mlsanity.com/paper/1904.08030/) (2019)
- [Controllable Multi-Interest Framework for Recommendation](https://mlsanity.com/paper/2005.09347/) (2020)
- [Global Context Enhanced Graph Neural Networks for Session-based Recommendation](https://mlsanity.com/paper/2106.05081/) (2021)
- [Sequence-Aware Recommender Systems](https://mlsanity.com/paper/1802.08452/) (2018)
- [Zero-Shot Next-Item Recommendation using Large Pretrained Language Models](https://mlsanity.com/paper/2304.03153/) (2023)
- [Efficiently Leveraging Multi-level User Intent for Session-based Recommendation via Atten-Mixer Network](https://mlsanity.com/paper/2206.12781/) (2022)
- [Chat-Driven Text Generation and Interaction for Person Retrieval](https://mlsanity.com/paper/2509.12662/) (2025)
- [Large Language Models for Intent-Driven Session Recommendations](https://mlsanity.com/paper/2312.07552/) (2023)
- [Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendation](https://mlsanity.com/paper/2502.02061/) (2025)
- [Multi-Modal Multi-Behavior Sequential Recommendation with Conditional Diffusion-Based Feature Denoising](https://mlsanity.com/paper/2508.05352/) (2025)
- [UniRec: A Dual Enhancement of Uniformity and Frequency in Sequential Recommendations](https://mlsanity.com/paper/2406.18470/) (2024)
- [Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction](https://mlsanity.com/paper/2508.21460/) (2025)
- [RaSeRec: Retrieval-Augmented Sequential Recommendation](https://mlsanity.com/paper/2412.18378/) (2024)
- [Coherency Improved Explainable Recommendation via Large Language Model](https://mlsanity.com/paper/2504.05315/) (2025)

## Built on by (most cited first, 1 of 1)

- [Anatomy of a Decision: Uncertainty-aware Hierarchical Intent Learning via Flow Matching for Multimodal Recommendation](https://mlsanity.com/paper/2609.29609/) (2026)

## Abstract (arXiv)

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.