# RecoWorld: Building Simulated Environments for Agentic Recommender Systems

arXiv: https://arxiv.org/abs/2509.10397 · HTML: https://mlsanity.com/paper/2509.10397/

## 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.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 30 of 54)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024)
- [Recommender Systems with Generative Retrieval](https://mlsanity.com/paper/2305.05065/) (2023)
- [Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations](https://mlsanity.com/paper/2402.17152/) (2024)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach](https://mlsanity.com/paper/2305.07001/) (2023)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [AgentScope: A Flexible yet Robust Multi-Agent Platform](https://mlsanity.com/paper/2402.14034/) (2024)
- [AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems](https://mlsanity.com/paper/2310.09233/) (2023)
- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [On Generative Agents in Recommendation](https://mlsanity.com/paper/2310.10108/) (2023)
- [UserBench: An Interactive Gym Environment for User-Centric Agents](https://mlsanity.com/paper/2507.22034/) (2025)
- [GenSim: A General Social Simulation Platform with Large Language Model based Agents](https://mlsanity.com/paper/2410.04360/) (2024)
- [A Survey on LLM-powered Agents for Recommender Systems](https://mlsanity.com/paper/2502.10050/) (2025)
- [Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation](https://mlsanity.com/paper/2403.09738/) (2024)
- [CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions](https://mlsanity.com/paper/2505.18878/) (2025)
- [NoteLLM-2: Multimodal Large Representation Models for Recommendation](https://mlsanity.com/paper/2405.16789/) (2024)
- [LLM-Powered User Simulator for Recommender System](https://mlsanity.com/paper/2412.16984/) (2024)
- [SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation](https://mlsanity.com/paper/2504.12722/) (2025)
- [KuaiSim: A Comprehensive Simulator for Recommender Systems](https://mlsanity.com/paper/2309.12645/) (2023)
- [LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities](https://mlsanity.com/paper/2405.06700/) (2024)
- [Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2503.16734/) (2025)

## Built on by (most cited first, 19 of 19)

- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [Training Proactive and Personalized LLM Agents](https://mlsanity.com/paper/2511.02208/) (2025)
- [Graph-based Agent Memory: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2602.05665/) (2026)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback](https://mlsanity.com/paper/2602.12612/) (2026)
- [RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems](https://mlsanity.com/paper/2605.11874/) (2026)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [Verifiable Reasoning for LLM-based Generative Recommendation](https://mlsanity.com/paper/2603.07725/) (2026)
- [Self-Distilled Reinforcement Learning for Co-Evolving Agentic Recommender Systems](https://mlsanity.com/paper/2604.10029/) (2026)
- [StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarios](https://mlsanity.com/paper/2605.25758/) (2026)
- [EvoRec: Self Evolving Agentic Recommender Systems](https://mlsanity.com/paper/2606.28368/) (2026)
- [Adaptive Tool Generation with Models as Tools and Reinforcement Learning](https://mlsanity.com/paper/2510.06825/) (2025)
- [Do Recommendation Algorithms Work When Users Are LLM Agents? A Case Study on Moltbook](https://mlsanity.com/paper/2606.29762/) (2026)
- [An LLM-powered Agentic Recommendation System for Connected TV Content Discovery](https://mlsanity.com/paper/2607.09988/) (2026)
- [Can We Steer the Black-Box? Towards Controllability-Centric Evaluation of Recommender Systems with Collaborative Agents](https://mlsanity.com/paper/2607.13418/) (2026)
- [A Behavioral Trait Leaks into Preferences: Diagnosing Trait Interference in LLM User Simulators](https://mlsanity.com/paper/2609.25572/) (2026)
- [ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents](https://mlsanity.com/paper/2609.37311/) (2026)
- [RealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commerce](https://mlsanity.com/paper/2609.38974/) (2026)
- [PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems](https://mlsanity.com/paper/2610.13989/) (2026)

## 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.