mlsanityData to 7 Oct 2026

R2ec: Towards Large Recommender Models with Reasoning

arXiv 2505.16994 ↗First posted 22 May 2025cs.IR cs.AI cs.CLcited by 13

On the map: LLM reasoning → LLM reasoning for recommendation

Abstract (arXiv)

Large recommender models have extended LLMs as powerful recommenders via encoding or item generation, and recent breakthroughs in LLM reasoning synchronously motivate the exploration of reasoning in recommendation. In this work, we propose R2ec, a unified large recommender model with intrinsic reasoning capability. R2ec introduces a dual-head architecture that supports both reasoning chain generation and efficient item prediction in a single model, significantly reducing inference latency. To overcome the lack of annotated reasoning data, we design RecPO, a reinforcement learning framework that optimizes reasoning and recommendation jointly with a novel fused reward mechanism. Extensive experiments on three datasets demonstrate that R2ec outperforms traditional, LLM-based, and reasoning-augmented recommender baselines, while further analyses validate its competitive efficiency among conventional LLM-based recommender baselines and strong adaptability to diverse recommendation scenarios. Code and checkpoints available at https://github.com/YRYangang/RRec.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning. Builds on 28 of its 47 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

28 of 47 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendation4 Feb
  2. 2024Review-driven Personalized Preference Reasoning with Large Language Models for Recommendation12 Aug
  3. 2024Leveraging LLM Reasoning Enhances Personalized Recommender Systems22 Jul
  4. 2024LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation3 Jul
  5. 2024Can Small Language Models be Good Reasoners for Sequential Recommendation?7 Mar

Other references · 23

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  5. 2025s1: Simple test-time scalingcited by 1,311
  6. 2018Self-Attentive Sequential Recommendationcited by 1,169
  7. 2018Personalized Top-N Sequential Recommendation via Convolutional Sequence Embeddingcited by 473
  8. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  9. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 291
  10. 2025Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learningcited by 260
  11. 2024Learnable Item Tokenization for Generative Recommendationcited by 106
  12. 2024Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMscited by 103
11 more
  1. 2024On Softmax Direct Preference Optimization for Recommendationcited by 64
  2. 2024HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modelingcited by 63
  3. 2023Large Language Model based Long-tail Query Rewriting in Taobao Searchcited by 61
  4. 2025Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedbackcited by 41
  5. 2025Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learningcited by 32
  6. 2024LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Applicationcited by 21
  7. 2024Inductive Generative Recommendation via Retrieval-based Speculationcited by 15
  8. 2025Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendationcited by 15
  9. 2024End-to-end Training for Recommendation with Language-based User Profilescited by 10
  10. 2024Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendationcited by 1
  11. 2024Laser: Parameter-Efficient LLM Bi-Tuning for Sequential Recommendation with Collaborative Informationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 10.

13 papers.

Sort:

By area:

  1. 2025Reinforced Latent Reasoning for LLM-based Recommendationcited by 46
  2. 2025Parallel Test-Time Scaling for Latent Reasoning Modelscited by 12
  3. 2026Reasoning over Semantic IDs Enhances Generative Recommendationcited by 12
  4. 2026Verifiable Reasoning for LLM-based Generative Recommendationcited by 2
  5. 2026SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendationcited by 2
  6. 2026HoloRec: Holistic Encoding and Interleaved Reasoning for Generative Recommendationcited by 2
  7. 2025MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedbackcited by 1
  8. 2026Reasoning to Rank: An End-to-End Solution for Exploiting Large Language Models for Recommendationcited by 1
  9. 2026Improving LLM-based Recommendation with Self-Hard Negatives from Intermediate Layerscited by 1
  10. 2026LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendationcited by 1
  11. 2026Think2Go: Generative Next POI Recommendation with LLM Reasoningcited by 1
  12. 2026Learning from Online User Feedback for Shopping Agentscited by 1
1 more
  1. 2026Efficient Multimodal Generative Recommendation with Latent Narrative Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Reinforced Preference Optimization for Reasoning-Augmented Recommendations
  2. 2025Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation
  3. 2026ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning
  4. 2026Towards Sample-Efficient and Stable Reinforcement Learning for LLM-based Recommendation
  5. 2026Harmonizing Semantic and Collaborative in LLMs: Reasoning-based Embedding Generator for Sequential Recommendation
  6. 2026RecRec: Latent Interests Recursive Reasoning for Sequential Recommendation ↗
  7. 2025MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMs
  8. 2024LLM is Knowledge Graph Reasoner: LLM's Intuition-aware Knowledge Graph Reasoning for Cold-start Sequential Recommendation