mlsanityData to 7 Oct 2026

RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation

arXiv 2605.07129 ↗First posted 8 May 2026cs.IR cs.AI cs.LGcited by 0

On the map: LLM reasoning → LLM reasoning for recommendation

Abstract (arXiv)

Large Language Models (LLMs) have emerged as a promising paradigm for next-generation recommender systems, offering strong semantic understanding and natural-language reasoning abilities. Despite recent progress, current LLM-based recommenders still face key challenges in constructing decision-relevant contexts from heterogeneous evidence. First, existing methods often rely on fixed context construction strategies: collaborative behavioral evidence and item-side metadata are typically incorporated through predefined prompts, static retrieval pipelines, or handcrafted injection mechanisms, making it difficult to determine what information is truly beneficial for each instance. Second, heterogeneous evidence introduces a severe context-efficiency bottleneck. Rich metadata and collaborative interaction records can quickly overwhelm the context window, while aggressive compression or heuristic filtering may discard fine-grained evidence critical for accurate recommendation. To address these challenges, we propose RRCM, a ranking-driven retrieval-and-reasoning framework over collaborative and metadata memories for LLM-based agentic recommendation. RRCM starts from a lightweight user-history context and learns whether to recommend directly, retrieve collaborative evidence, retrieve item metadata, or interleave both through reasoning. Both memories are represented in natural language and accessed through a unified retrieval interface, enabling flexible evidence acquisition without handcrafted CF injection or fixed retrieval rules. We optimize this memory-reading policy with an outcome-only ranking reward, instantiated using group relative policy optimization, so that retrieval decisions are directly driven by final top-k recommendation quality. Extensive experiments show that RRCM significantly outperforms traditional baselines and diverse LLM-based recommendation approaches.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning. Builds on 43 of its 54 references that are in the map. First posted on arXiv 8 May 2026.

Builds on

43 of 54 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning23 Oct
  2. 2025Reinforced Latent Reasoning for LLM-based Recommendation25 May
  3. 2025DeepRec: Towards a Deep Dive Into the Item Space with Large Language Model Based Recommendation22 May
  4. 2025Improving LLM-powered Recommendations with Personalized Information19 Feb
  5. 2025Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendation4 Feb
  6. 2024Leveraging LLM Reasoning Enhances Personalized Recommender Systems22 Jul

Other references · 37

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  7. 2025Qwen3 Technical Reportcited by 8,195
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  9. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  10. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  11. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  12. 2018Self-Attentive Sequential Recommendationcited by 1,169
25 more
  1. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  2. 2015Session-based Recommendations with Recurrent Neural Networkscited by 685
  3. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 517
  4. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  5. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 396
  6. 2023A Survey on Large Language Models for Recommendationcited by 378
  7. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 217
  8. 2023RecMind: Large Language Model Powered Agent For Recommendationcited by 129
  9. 2023Retrieval meets Long Context Large Language Modelscited by 114
  10. 2023CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendationcited by 99
  11. 2023Cognitive Mirage: A Review of Hallucinations in Large Language Modelscited by 83
  12. 2023A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systemscited by 73
  13. 2024On Softmax Direct Preference Optimization for Recommendationcited by 64
  14. 2024HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modelingcited by 63
  15. 2025Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendationcited by 56
  16. 2025Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learningcited by 32
  17. 2024Text-like Encoding of Collaborative Information in Large Language Models for Recommendationcited by 25
  18. 2023Knowledge Graph Self-Supervised Rationalization for Recommendationcited by 22
  19. 2024SPRec: Self-Play to Debias LLM-based Recommendationcited by 18
  20. 2025Collaborative Retrieval for Large Language Model-based Conversational Recommender Systemscited by 16
  21. 2026MemRec: Collaborative Memory-Augmented Agentic Recommender Systemcited by 15
  22. 2025RecGPT Technical Reportcited by 11
  23. 2025Breaking the Top-K Barrier: Advancing Top-K Ranking Metrics Optimization in Recommender Systemscited by 9
  24. 2024STAR: A Simple Training-free Approach for Recommendations using Large Language Modelscited by 8
  25. 2025HyMiRec: A Hybrid Multi-interest Learning Framework for LLM-based Sequential Recommendationcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation
  2. 2025LLMs as Better Recommenders with Natural Language Collaborative Signals: A Self-Assessing Retrieval Approach
  3. 2025A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges
  4. 2024All Roads Lead to Rome: Unveiling the Trajectory of Recommender Systems Across the LLM Era
  5. 2026AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders
  6. 2024Aligning Large Language Models with Recommendation Knowledge
  7. 2025EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration
  8. 2025AgentDR: Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents