# Qwen-AgentWorld: Language World Models for General Agents

arXiv: https://arxiv.org/abs/2606.24597 · HTML: https://mlsanity.com/paper/2606.24597/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 102 of its 135 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 102)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022)
- [Diffusion Models Are Real-Time Game Engines](https://mlsanity.com/paper/2408.14837/) (2024)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [ZeroSearch: Incentivize the Search Capability of LLMs without Searching](https://mlsanity.com/paper/2505.04588/) (2025)
- [World Simulation with Video Foundation Models for Physical AI](https://mlsanity.com/paper/2511.00062/) (2025)
- [GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks](https://mlsanity.com/paper/2510.04374/) (2025)
- [Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents](https://mlsanity.com/paper/2411.06559/) (2024)
- [Training Agents Inside of Scalable World Models](https://mlsanity.com/paper/2509.24527/) (2025)
- [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024)
- [CWM: An Open-Weights LLM for Research on Code Generation with World Models](https://mlsanity.com/paper/2510.02387/) (2025)
- [Agent Learning via Early Experience](https://mlsanity.com/paper/2510.08558/) (2025)
- [The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution](https://mlsanity.com/paper/2510.25726/) (2025)
- [Vid2World: Crafting Video Diffusion Models to Interactive World Models](https://mlsanity.com/paper/2505.14357/) (2025)
- [WideSearch: Benchmarking Agentic Broad Info-Seeking](https://mlsanity.com/paper/2508.07999/) (2025)
- [Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning](https://mlsanity.com/paper/2602.10090/) (2026)
- [EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis](https://mlsanity.com/paper/2601.05808/) (2026)
- [VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents](https://mlsanity.com/paper/2510.16907/) (2025)

## Built on by (most cited first, 28 of 28)

- [EnvHarness: Awakening Static Worlds for Agent Learning](https://mlsanity.com/paper/2608.19880/) (2026)
- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [Harness-Zero: Harness Distillation via Agent-as-Harness](https://mlsanity.com/paper/2609.24974/) (2026)
- [AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents](https://mlsanity.com/paper/2608.05891/) (2026)
- [EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning](https://mlsanity.com/paper/2608.06197/) (2026)
- [AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale](https://mlsanity.com/paper/2608.20634/) (2026)
- [Dual-Frontier: When Can an Agent Trust Its World Model?](https://mlsanity.com/paper/2609.26293/) (2026)
- [Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents](https://mlsanity.com/paper/2609.39982/) (2026)
- [Volumetric Radiology AI in the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2608.20549/) (2026)
- [Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy](https://mlsanity.com/paper/2608.21325/) (2026)
- [World Model-Guided Reinforcement Learning via Counterfactual User Engagement Simulation](https://mlsanity.com/paper/2609.01067/) (2026)
- [Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format](https://mlsanity.com/paper/2609.09882/) (2026)
- [Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL](https://mlsanity.com/paper/2609.20715/) (2026)
- [Agent-Editing World Model: Rethinking World Modeling for LLM Agents](https://mlsanity.com/paper/2609.28416/) (2026)
- [Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning](https://mlsanity.com/paper/2609.28963/) (2026)
- [ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds](https://mlsanity.com/paper/2609.30199/) (2026)
- [CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning](https://mlsanity.com/paper/2609.32750/) (2026)
- [CompoWorld: Compositional Environment Scaling for General Agents](https://mlsanity.com/paper/2609.33665/) (2026)
- [TomasuLLM: Out-of-Order Speculative Execution for LLM Agents](https://mlsanity.com/paper/2609.38201/) (2026)
- [WorkGenesis: Building the Worlds That Teach Agents to Work](https://mlsanity.com/paper/2609.39325/) (2026)
- [Federated Agent Optimization](https://mlsanity.com/paper/2610.01195/) (2026)
- [AutoGUIWorld: Image Generators as Visual World Models for GUI Agent](https://mlsanity.com/paper/2610.01215/) (2026)
- [SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting](https://mlsanity.com/paper/2610.04109/) (2026)
- [From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation](https://mlsanity.com/paper/2610.06100/) (2026)
- [Long-Horizon Textual World Modeling through Structured Reasoning](https://mlsanity.com/paper/2610.06637/) (2026)
- [AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model](https://mlsanity.com/paper/2610.08773/) (2026)
- [ProgAgent: Learning Tool Orchestration through Programmatic Training](https://mlsanity.com/paper/2610.14774/) (2026)
- [Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents](https://mlsanity.com/paper/2610.18082/) (2026)

## Abstract (arXiv)

A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning. In this work, we investigate how world modeling based on language models can further push the boundaries of general agents. (i) We first focus on building foundation models for agentic environment simulation. We introduce Qwen-AgentWorld-35B-A3B and Qwen-AgentWorld-397B-A17B, the first language world models capable of simulating agentic environments covering 7 domains via long chain-of-thought reasoning. Leveraging more than 10M environment interaction trajectories of 7 domains in real-world environments, we develop Qwen-AgentWorld through a three-stage training pipeline: CPT injects general-purpose world modeling capabilities from the state transition dynamics and augmented professional corpora, SFT activates next-state-prediction reasoning, and RL sharpens simulation fidelity through a tailored framework with hybrid rubric-and-rule rewards. To evaluate language world models, we present AgentWorldBench, a comprehensive benchmark constructed from real-world interactions of 5 frontier models on 9 established benchmarks. Empirical results demonstrate that Qwen-AgentWorld significantly outperforms existing frontier models. (ii) Beyond foundation models, we further investigate two complementary paradigms through which world modeling enhances general agents. First, as a decoupled environment simulator, Qwen-AgentWorld supports scalable and controllable simulation of thousands of real-world environments for agentic RL, yielding gains that surpass real-environment training alone. Second, as a unified agent foundation model, world-model training acts as a highly effective warm-up that improves downstream performance across 7 agentic benchmarks. Code: https://github.com/QwenLM/Qwen-AgentWorld