mlsanityData to 7 Oct 2026

Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning

arXiv 2503.24289 ↗First posted 31 Mar 2025cs.IR cs.CLcited by 32

Not on the map. Why?

Cited by 21 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose Rec-R1, a general reinforcement learning framework that bridges large language models (LLMs) with recommendation systems through closed-loop optimization. Unlike prompting and supervised fine-tuning (SFT), Rec-R1 directly optimizes LLM generation using feedback from a fixed black-box recommendation model, without relying on synthetic SFT data from proprietary models such as GPT-4o. This avoids the substantial cost and effort required for data distillation. To verify the effectiveness of Rec-R1, we evaluate it on two representative tasks: product search and sequential recommendation. Experimental results demonstrate that Rec-R1 not only consistently outperforms prompting- and SFT-based methods, but also achieves significant gains over strong discriminative baselines, even when used with simple retrievers such as BM25. Moreover, Rec-R1 preserves the general-purpose capabilities of the LLM, unlike SFT, which often impairs instruction-following and reasoning. These findings suggest Rec-R1 as a promising foundation for continual task-specific adaptation without catastrophic forgetting.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 70 of its 88 references that are in the map. First posted on arXiv 31 Mar 2025.

Builds on

70 of 88 references.

References · 70

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  6. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  7. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  8. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  9. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  10. 2024Qwen2.5 Technical Reportcited by 4,713
  11. 2021Program Synthesis with Large Language Modelscited by 3,509
  12. 2015Trust Region Policy Optimizationcited by 2,503
38 more
  1. 2017Billion-scale similarity search with GPUscited by 2,477
  2. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  3. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  4. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  5. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  6. 2018Self-Attentive Sequential Recommendationcited by 1,169
  7. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  8. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,143
  9. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  10. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 396
  11. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 336
  12. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 307
  13. 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 241
  14. 2024Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoderscited by 213
  15. 2023Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approachcited by 168
  16. 2023Representation Learning with Large Language Models for Recommendationcited by 155
  17. 2022M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systemscited by 152
  18. 2023How Can Recommender Systems Benefit from Large Language Models: A Surveycited by 141
  19. 2023Large Language Models as Zero-Shot Conversational Recommenderscited by 126
  20. 2022Towards Universal Sequence Representation Learning for Recommender Systemscited by 120
  21. 2023Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendationcited by 113
  22. 2023GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretationcited by 101
  23. 2023PALR: Personalization Aware LLMs for Recommendationcited by 96
  24. 2020Towards Topic-Guided Conversational Recommender Systemcited by 94
  25. 2023LLM-Rec: Personalized Recommendation via Prompting Large Language Modelscited by 77
  26. 2023Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Searchcited by 74
  27. 2023Towards Open-World Recommendation with Knowledge Augmentation from Large Language Modelscited by 74
  28. 2018Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learningcited by 71
  29. 2023Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewritingcited by 69
  30. 2023GenRec: Large Language Model for Generative Recommendationcited by 62
  31. 2023Large Language Model based Long-tail Query Rewriting in Taobao Searchcited by 61
  32. 2022Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Searchcited by 58
  33. 2023LLaRA: Large Language-Recommendation Assistantcited by 56
  34. 2020Self-Supervised Reinforcement Learning for Recommender Systemscited by 49
  35. 2023EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commercecited by 48
  36. 2023RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendationcited by 36
  37. 2021Personalized News Recommendation: Methods and Challengescited by 30
  38. 2024Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregationcited by 26

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 14; 2026: 18.

32 papers.

Sort:

By area:

  1. 2025An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agentscited by 43
  2. 2025SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMscited by 23
  3. 2025Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shoppingcited by 16
  4. 2025Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewardscited by 14
  5. 2025Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learningcited by 14
  6. 2025R2ec: Towards Large Recommender Models with Reasoningcited by 13
  7. 2025Slow Thinking for Sequential Recommendationcited by 11
  8. 2025Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learningcited by 10
  9. 2025MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMscited by 9
  10. 2025PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimizationcited by 8
  11. 2025Generative Reasoning Recommendation via LLMscited by 5
  12. 2026S2GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendationcited by 5
20 more
  1. 2025Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learningcited by 3
  2. 2026PROMISE: Process Reward Models Unlock Test-Time Scaling Laws in Generative Recommendationscited by 2
  3. 2026Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-trainingcited by 2
  4. 2026SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendationcited by 2
  5. 2025R1-Ranker: Teaching LLM Rankers to Reasoncited by 1
  6. 2025MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedbackcited by 1
  7. 2026Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMscited by 1
  8. 2026LLM Agents Enable User-Governed Personalization Beyond Platform Boundariescited by 1
  9. 2026Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Targetcited by 1
  10. 2026Self-supervised User Profile Generation for Personalizationcited by 1
  11. 2026RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systemscited by 0
  12. 2026FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learningcited by 0
  13. 2026Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversationcited by 0
  14. 2026Enhancing Local Life Service Recommendation with Agentic Reasoning in Large Language Modelcited by 0
  15. 2026ReCast: Recasting Learning Signals for Reinforcement Learning in Generative Recommendationcited by 0
  16. 2026RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendationcited by 0
  17. 2026ExpWeaver: LLM Agents Learn from Experience via Latent RAGcited by 0
  18. 2026Harmonizing Semantic and Collaborative in LLMs: Reasoning-based Embedding Generator for Sequential Recommendationcited by 0
  19. 2026Beyond Supervised Clarification: Input Rewriting with LLMs for Dialogue Discourse Parsingcited by 0
  20. 2026SelfDR: Self-Distillation from Reasoning for LLM-Based Recommendationcited by 0