mlsanityData to 14 Oct 2026

RecoWorld: Building Simulated Environments for Agentic Recommender Systems

arXiv 2509.10397 ↗First posted 12 Sep 2025cs.IRcited by 19

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

Abstract (arXiv)

We present RecoWorld, a blueprint for building simulated environments tailored to agentic recommender systems. Such environments give agents a proper training space where they can learn from errors without impacting real users. RecoWorld distinguishes itself with a dual-view architecture: a simulated user and an agentic recommender engage in multi-turn interactions aimed at maximizing user retention. The user simulator reviews recommended items, updates its mindset, and when sensing potential user disengagement, generates reflective instructions. The agentic recommender adapts its recommendations by incorporating these user instructions and reasoning traces, creating a dynamic feedback loop that actively engages users. This process leverages the exceptional reasoning capabilities of modern LLMs. We explore diverse content representations within the simulator, including text-based, multimodal, and semantic ID modeling, and discuss how multi-turn RL enables the recommender to refine its strategies through iterative interactions. RecoWorld also supports multi-agent simulations, allowing creators to simulate the responses of targeted user populations. It marks an important first step toward recommender systems where users and agents collaboratively shape personalized information streams. We envision new interaction paradigms where "user instructs, recommender responds," jointly optimizing user retention and engagement.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use. Builds on 54 of its 75 references that are in the map. First posted on arXiv 12 Sep 2025.

Builds on

54 of 75 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems2 Jul
  2. 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems26 May
  3. 2025Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models20 Mar
  4. 2025iAgent: LLM Agent as a Shield between User and Recommender Systems20 Feb
  5. 2025A Survey on LLM-powered Agents for Recommender Systems14 Feb
  6. 2024Agentic Feedback Loop Modeling Improves Recommendation and User Simulation26 Oct
  7. 2023On Generative Agents in Recommendation16 Oct
  8. 2023AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems13 Oct

Other references · 46

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  3. 2016OpenAI Gymcited by 1,736
  4. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
  5. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  6. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 748
  7. 2024TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Taskscited by 326
  8. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agentscited by 208
  9. 2023Recommender Systems with Generative Retrievalcited by 198
  10. 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendationscited by 188
  11. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 186
  12. 2025OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignmentcited by 173
34 more
  1. 2023Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approachcited by 168
  2. 2023User Behavior Simulation with Large Language Model based Agentscited by 140
  3. 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 132
  4. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 121
  5. 2025LLM Social Simulations Are a Promising Research Methodcited by 99
  6. 2025UserBench: An Interactive Gym Environment for User-Centric Agentscited by 76
  7. 2024GenSim: A General Social Simulation Platform with Large Language Model based Agentscited by 50
  8. 2024Evaluating Large Language Models as Generative User Simulators for Conversational Recommendationcited by 48
  9. 2025CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactionscited by 47
  10. 2024NoteLLM-2: Multimodal Large Representation Models for Recommendationcited by 44
  11. 2024LLM-Powered User Simulator for Recommender Systemcited by 39
  12. 2025SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluationcited by 33
  13. 2023KuaiSim: A Comprehensive Simulator for Recommender Systemscited by 30
  14. 2024LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunitiescited by 27
  15. 2024On the limits of agency in agent-based modelscited by 21
  16. 2025Enhancing Embedding Representation Stability in Recommendation Systems with Semantic IDcited by 19
  17. 2025ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendationcited by 18
  18. 2025REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systemscited by 18
  19. 2024LLMs for User Interest Exploration in Large-scale Recommendation Systemscited by 15
  20. 2025Can LLM-Simulated Practice and Feedback Upskill Human Counselors? A Randomized Study with 90+ Novice Counselorscited by 13
  21. 2025RecUserSim: A Realistic and Diverse User Simulator for Evaluating Conversational Recommender Systemscited by 12
  22. 2024SUBER: An RL Environment with Simulated Human Behavior for Recommender Systemscited by 11
  23. 2024Knowledge Graph Enhanced Language Agents for Recommendationcited by 11
  24. 2025Towards Better Instruction Following Retrieval Modelscited by 9
  25. 2025VRAgent-R1: Boosting Video Recommendation with MLLM-based Agents via Reinforcement Learningcited by 8
  26. 2025Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendationcited by 7
  27. 2025Hierarchical Tree Search-based User Lifelong Behavior Modeling on Large Language Modelcited by 6
  28. 2023SARDINE: A Simulator for Automated Recommendation in Dynamic and Interactive Environmentscited by 5
  29. 2025Exploring the Impact of Personality Traits on Conversational Recommender Systems: A Simulation with Large Language Modelscited by 5
  30. 2025Long-Term Interest Clock: Fine-Grained Time Perception in Streaming Recommendation Systemcited by 3
  31. 2025GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networkscited by 3
  32. 2024OMuleT: Orchestrating Multiple Tools for Practicable Conversational Recommendationcited by 2
  33. 2025DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Rewardcited by 2
  34. 2025Value Function Decomposition in Markov Recommendation Processcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 16.

19 papers.

Sort:

By area:

  1. 2026Code as Agent Harnesscited by 47
  2. 2025Training Proactive and Personalized LLM Agentscited by 46
  3. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 25
  4. 2025A Survey on Agentic Multimodal Large Language Modelscited by 23
  5. 2026Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedbackcited by 10
  6. 2026RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systemscited by 4
  7. 2026Autonomous Information Seeking: A Roadmap for Agentic Recommender Systemscited by 4
  8. 2026Verifiable Reasoning for LLM-based Generative Recommendationcited by 2
  9. 2026Self-Distilled Reinforcement Learning for Co-Evolving Agentic Recommender Systemscited by 1
  10. 2026StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarioscited by 1
  11. 2026EvoRec: Self Evolving Agentic Recommender Systemscited by 1
  12. 2025Adaptive Tool Generation with Models as Tools and Reinforcement Learningcited by 0
7 more
  1. 2026Do Recommendation Algorithms Work When Users Are LLM Agents? A Case Study on Moltbookcited by 0
  2. 2026An LLM-powered Agentic Recommendation System for Connected TV Content Discoverycited by 0
  3. 2026Can We Steer the Black-Box? Towards Controllability-Centric Evaluation of Recommender Systems with Collaborative Agentscited by 0
  4. 2026A Behavioral Trait Leaks into Preferences: Diagnosing Trait Interference in LLM User Simulatorscited by 0
  5. 2026ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agentscited by 0
  6. 2026RealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commercecited by 0
  7. 2026PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems
  2. 2026RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation
  3. 2026RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents
  4. 2026τ-Rec: A Verifiable Benchmark for Agentic Recommender Systems
  5. 2026AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side
  6. 2025Multi-Agent Collaborative Filtering: Orchestrating Users and Items for Agentic Recommendations
  7. 2026Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation
  8. 2026Rethinking Recommendation Paradigms: From Pipelines to Agentic Recommender Systems