mlsanityData to 7 Oct 2026

On Generative Agents in Recommendation

arXiv 2310.10108 ↗First posted 16 Oct 2023cs.IR cs.AIcited by 88

On the map: LLM agents and tool use → Agentic recommender systems

Abstract (arXiv)

Recommender systems are the cornerstone of today's information dissemination, yet a disconnect between offline metrics and online performance greatly hinders their development. Addressing this challenge, we envision a recommendation simulator, capitalizing on recent breakthroughs in human-level intelligence exhibited by Large Language Models (LLMs). We propose Agent4Rec, a user simulator in recommendation, leveraging LLM-empowered generative agents equipped with user profile, memory, and actions modules specifically tailored for the recommender system. In particular, these agents' profile modules are initialized using real-world datasets (e.g. MovieLens, Steam, Amazon-Book), capturing users' unique tastes and social traits; memory modules log both factual and emotional memories and are integrated with an emotion-driven reflection mechanism; action modules support a wide variety of behaviors, spanning both taste-driven and emotion-driven actions. Each agent interacts with personalized recommender models in a page-by-page manner, relying on a pre-implemented collaborative filtering-based recommendation algorithm. We delve into both the capabilities and limitations of Agent4Rec, aiming to explore an essential research question: ``To what extent can LLM-empowered generative agents faithfully simulate the behavior of real, autonomous humans in recommender systems?'' Extensive and multi-faceted evaluations of Agent4Rec highlight both the alignment and deviation between agents and user-personalized preferences. Beyond mere performance comparison, we explore insightful experiments, such as emulating the filter bubble effect and discovering the underlying causal relationships in recommendation tasks. Our codes are available at https://github.com/LehengTHU/Agent4Rec.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use. Builds on 40 of its 81 references that are in the map. First posted on arXiv 16 Oct 2023.

Builds on

40 of 81 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations31 Aug
  2. 2023RecMind: Large Language Model Powered Agent For Recommendation28 Aug

Other references · 38

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  5. 2017Billion-scale similarity search with GPUscited by 2,477
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  7. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  8. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  9. 2018Self-Attentive Sequential Recommendationcited by 1,169
  10. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  11. 2015Image-based Recommendations on Styles and Substitutescited by 702
  12. 2018Variational Autoencoders for Collaborative Filteringcited by 308
26 more
  1. 2023Language Models Represent Space and Timecited by 306
  2. 2023Tool Learning with Foundation Modelscited by 302
  3. 2019Challenges of Real-World Reinforcement Learningcited by 282
  4. 2020Bias and Debias in Recommender System: A Survey and Future Directionscited by 239
  5. 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolfcited by 238
  6. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 228
  7. 2021Reinforcement learning based recommender systems: A surveycited by 187
  8. 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 171
  9. 2017Deep Learning based Recommender System: A Survey and New Perspectivescited by 136
  10. 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Modelscited by 92
  11. 2019RecSim: A Configurable Simulation Platform for Recommender Systemscited by 91
  12. 2020Feedback Loop and Bias Amplification in Recommender Systemscited by 89
  13. 2023AgentSims: An Open-Source Sandbox for Large Language Model Evaluationcited by 86
  14. 2023Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examplescited by 84
  15. 2018Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learningcited by 80
  16. 2018RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertisingcited by 65
  17. 2018Generative Adversarial User Model for Reinforcement Learning Based Recommendation Systemcited by 64
  18. 2022Causal Inference in Recommender Systems: A Survey and Future Directionscited by 44
  19. 2022CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender Systemcited by 38
  20. 2023Towards autonomous system: flexible modular production system enhanced with large language model agentscited by 38
  21. 2022Incorporating Bias-aware Margins into Contrastive Loss for Collaborative Filteringcited by 29
  22. 2023Invariant Collaborative Filtering to Popularity Distribution Shiftcited by 23
  23. 2021Top-N Recommendation with Counterfactual User Preference Simulationcited by 21
  24. 2023A large language model-assisted education tool to provide feedback on open-ended responsescited by 21
  25. 2022CausPref: Causal Preference Learning for Out-of-Distribution Recommendationcited by 17
  26. 2023Boosting Differentiable Causal Discovery via Adaptive Sample Reweightingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 25; 2025: 32; 2026: 30.

88 papers.

Sort:

By area:

  1. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  2. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 253
  3. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  4. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 201
  5. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  6. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 180
  7. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 167
  8. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospectscited by 130
  9. 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 127
  10. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialoguecited by 121
  11. 2025Multi-Agent Collaboration via Evolving Orchestrationcited by 102
  12. 2024On Softmax Direct Preference Optimization for Recommendationcited by 64
38 more
  1. 2024Can Large Language Model Agents Simulate Human Trust Behavior?cited by 62
  2. 2025DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agentscited by 59
  3. 2024Agents' Room: Narrative Generation through Multi-step Collaborationcited by 57
  4. 2025A Survey on LLM-powered Agents for Recommender Systemscited by 49
  5. 2024ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluationcited by 46
  6. 2025Reinforced Latent Reasoning for LLM-based Recommendationcited by 46
  7. 2024EduAgent: Generative Student Agents in Learningcited by 41
  8. 2024How Reliable is Your Simulator? Analysis on the Limitations of Current LLM-based User Simulators for Conversational Recommendationcited by 25
  9. 2025AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendationscited by 23
  10. 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systemscited by 23
  11. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  12. 2024MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimizationcited by 20
  13. 2024Language Representations Can be What Recommenders Need: Findings and Potentialscited by 18
  14. 2025RecoWorld: Building Simulated Environments for Agentic Recommender Systemscited by 18
  15. 2025A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigmscited by 17
  16. 2024Agentic Feedback Loop Modeling Improves Recommendation and User Simulationcited by 16
  17. 2025MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructionscited by 16
  18. 2025The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systemscited by 14
  19. 2024A LLM-based Controllable, Scalable, Human-Involved User Simulator Framework for Conversational Recommender Systemscited by 12
  20. 2025AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platformscited by 12
  21. 2024Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Reviewcited by 11
  22. 2026PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimizationcited by 10
  23. 2025Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Researchcited by 9
  24. 2025Stochastic Self-Organization in Multi-Agent Systemscited by 9
  25. 2024Mitigating Propensity Bias of Large Language Models for Recommender Systemscited by 8
  26. 2025CARTS: Collaborative Agents for Recommendation Textual Summarizationcited by 6
  27. 2026RoboRouter: Training-Free Policy Routing for Robotic Manipulationcited by 6
  28. 2026Multi-Agent Video Recommenders: Evolution, Patterns, and Open Challengescited by 6
  29. 2024TravelAgent: Generative Agents in the Built Environmentcited by 5
  30. 2025CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Modelscited by 5
  31. 2024Apollonion: Profile-centric Dialog Agentcited by 4
  32. 2025Cross-Task Experiential Learning on LLM-based Multi-Agent Collaborationcited by 4
  33. 2026SimGym: Traffic-Grounded Browser Agents for Offline A/B Testing in E-Commercecited by 4
  34. 2026Agentic Recommender System with Hierarchical Belief-State Memorycited by 4
  35. 2025GGBond: Growing Graph-Based AI-Agent Society for Socially-Aware Recommender Simulationcited by 3
  36. 2025Co-Saving: Resource Aware Multi-Agent Collaboration for Software Developmentcited by 3
  37. 2025AgentDR: Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agentscited by 3
  38. 2026Exploring Recommender System Evaluation: A Multi-Modal User Agent Framework for A/B Testingcited by 3

50 most cited of 88 All 88 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Generative Recommendation: Data, Model, and Tasks
  2. 2023AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems
  3. 2026AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders
  4. 2026Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems
  5. 2025Temporal-Aware User Behaviour Simulation with Large Language Models for Recommender Systems
  6. 2025Dynamic Evaluation Framework for Personalized and Trustworthy Agents: A Multi-Session Approach to Preference Adaptability
  7. 2026Rethinking Recommendation Paradigms: From Pipelines to Agentic Recommender Systems
  8. 2024Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems