Qwen-AgentWorld：通用智能体语言世界模型
Qwen-AgentWorld: Language World Models for General Agents
摘要
世界模型基于当前的观测数据和行为来预测环境动态，是推理和规划过程中的核心认知机制。在本研究中，我们探讨了基于语言模型的世界建模如何进一步拓展通用智能体的能力边界。(i) 我们首先致力于构建用于智能体环境模拟的基础模型。我们推出了Qwen-AgentWorld-35B-A3B和Qwen-AgentWorld-397B-A17B这两款语言世界模型，它们能够通过长链推理方式模拟涵盖7个领域的智能体环境。利用现实世界中7个领域超过1000万条环境交互数据，我们通过三阶段训练流程来开发Qwen-AgentWorld：CPT阶段从状态转换动态和专业语料库中获取通用世界建模能力；SFT阶段激活下一状态的预测推理能力；RL阶段则通过混合评分与规则奖励机制来提高模拟精度。为了评估这些语言世界模型，我们建立了AgentWorldBench这一综合测试平台，该平台基于5种前沿模型在9个标准测试中的实际交互数据而构建。实验结果表明，Qwen-AgentWorld的性能显著优于现有前沿模型。(ii) 除了基础模型之外，我们还研究了两种互补的模型构建方法，通过这些方法可以提升通用智能体的能力。首先，作为独立的环境模拟器，Qwen-AgentWorld能够实现对数千个现实环境的可扩展且可控的模拟，从而帮助智能体强化学习取得更好的效果，其效果甚至超过了单纯使用真实环境进行训练的效果。其次，作为统一的智能体基础模型，世界模型训练可以作为一种有效的热身过程，从而提升7个智能体测试中的整体性能。代码链接：https://github.com/QwenLM/Qwen-AgentWorld
English Abstract
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