AtomRec: Evolving Atomic Memory for Agentic Recommendation
On the map: LLM agents and tool use → Agentic recommender systems
Abstract (arXiv)
Agentic recommender systems use large language models to maintain semantic memory and support evidence-aware recommendation. However, existing memory mechanisms often compress user and item information into coarse summaries and connect them with scalar collaborative links, making it difficult to preserve fine-grained preference stages or retrieve interpretable evidence as user interests evolve. We propose textscAtomRec, an agentic recommender with evolving atomic collaborative memory. textscAtomRec represents user and item memories as structured atomic units, builds semantic links across related memories, and evolves related historical fields when new interactions arrive. During recommendation, it retrieves linked memories as multi-hop evidence paths rather than isolated neighbor summaries, allowing collaborative signals to support grounded ranking. Experiments on four public benchmarks show that textscAtomRec consistently outperforms state-of-the-art agentic and memory-augmented baselines, with around 8.5% average relative improvement across metrics.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use. Builds on 59 of its 84 references that are in the map. First posted on arXiv 4 Sep 2026.
Builds on
59 of 84 references.
Closest ancestors · 9
Same direction, newest first
- 2026RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation10 Mar
- 2026ChainRec: An Agentic Recommender Learning to Route Tool Chains for Diverse and Evolving Interests11 Feb
- 2026MemRec: Collaborative Memory-Augmented Agentic Recommender System13 Jan
- 2025A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval7 Mar
- 2025iAgent: LLM Agent as a Shield between User and Recommender Systems20 Feb
- 2025A Survey on LLM-powered Agents for Recommender Systems14 Feb
- 2024MACRec: a Multi-Agent Collaboration Framework for Recommendation23 Feb
- 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations31 Aug
- 2023RecMind: Large Language Model Powered Agent For Recommendation28 Aug
Other references · 50
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
- 2018Self-Attentive Sequential Recommendationcited by 1,184
- 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
- 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
- 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
- 2015Image-based Recommendations on Styles and Substitutescited by 706
- 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
- 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 463
38 more
- 2023A Survey on Large Language Models for Recommendationcited by 379
- 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 337
- 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 309
- 2025Memory in the Age of AI Agentscited by 303
- 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 242
- 2023Is ChatGPT a Good Recommender? A Preliminary Studycited by 193
- 2025A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systemscited by 183
- 2023Adapting Large Language Models by Integrating Collaborative Semantics for Recommendationcited by 179
- 2023Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approachcited by 168
- 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
- 2025The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1cited by 91
- 2025MemInsight: Autonomous Memory Augmentation for LLM Agentscited by 85
- 2026XSkill: Continual Learning from Experience and Skills in Multimodal Agentscited by 75
- 2024A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)cited by 58
- 2025Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decodingcited by 43
- 2025MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosiscited by 32
- 2025MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversationcited by 29
- 2025Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Spacecited by 28
- 2025A Survey of Personalization: From RAG to Agentcited by 27
- 2025Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflowscited by 27
- 2026AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarioscited by 23
- 2025Pathology-Aware Prototype Evolution via LLM-Driven Semantic Disambiguation for Multicenter Diabetic Retinopathy Diagnosiscited by 22
- 2025Generative Recommendation with Semantic IDs: A Practitioner's Handbookcited by 18
- 2025MiniOneRec: An Open-Source Framework for Scaling Generative Recommendationcited by 17
- 2025Multi-Modal Multi-Behavior Sequential Recommendation with Conditional Diffusion-Based Feature Denoisingcited by 14
- 2026MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolutioncited by 12
- 2024Large Language Model Enhanced Recommender Systems: A Surveycited by 10
- 2026SafePro: Evaluating the Safety of Professional-Level AI Agentscited by 10
- 2025From IDs to Semantics: A Generative Framework for Cross-Domain Recommendation with Adaptive Semantic Tokenizationcited by 9
- 2026Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMscited by 8
- 2025Harnessing Light for Cold-Start Recommendations: Leveraging Epistemic Uncertainty to Enhance Performance in User-Item Interactionscited by 3
- 2025Semantic-Preserving Prompt Hijacking: A Black-Box Adversarial Attack on Auto-Prompt Optimizationcited by 3
- 2026MM-StanceDet: Retrieval-Augmented Multi-modal Multi-agent Stance Detectioncited by 3
- 2026Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RLcited by 3
- 2025Uncertainty-Aware Semantic Decoding for LLM-Based Sequential Recommendationcited by 2
- 2026Learn Before Represent: Bridging Generative and Contrastive Learning for Domain-Specific LLM Embeddingscited by 2
- 2025LLM-Driven Completeness and Consistency Evaluation for Cultural Heritage Data Augmentation in Cross-Modal Retrievalcited by 1
- 2026OneModel: A Unified Foundation for Platform-Scale Multi-Scenario Rankingcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders
- 2026When Memory Takes Gradients: Collaborative Vector Memory for Agentic Recommender Systems
- 2026Agentic Recommender System with Hierarchical Belief-State Memory
- 2026From Atom to Community: Structured and Evolving Agent Memory for User Behavior Modeling
- 2026Seeing and Reflecting: Multimodal Memory-Enhanced Agent Collaboration for Recommendation
- 2026RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
- 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
- 2023On Generative Agents in Recommendation