Large Language Models (LLMs) have recently shown strong reasoning and generalization capabilities, motivating their use as decision-making policies in complex environments. StarCraft II (SC2), with its massive state-action space and partial observability, is a challenging testbed. However, existing LLM-based SC2 agents primarily focus on improving the policy itself and overlook integrating a learnable, action-conditioned transition model into the decision loop. To bridge this gap, we propose StarWM, the first world model for SC2 that predicts future observations under partial observability. To facilitate learning SC2's hybrid dynamics, we introduce a structured textual representation that factorizes observations into five semantic modules, and construct SC2-Dynamics-50k, the first instruction-tuning dataset for SC2 dynamics prediction. We further develop a multi-dimensional offline evaluation framework for predicted structured observations. Offline results show StarWM's substantial gains over zero-shot baselines, including nearly 60% improvements in resource prediction accuracy and self-side macro-situation consistency. Finally, we propose StarWM-Agent, a world-model-augmented decision system that integrates StarWM into a Generate--Simulate--Refine decision loop for foresight-driven policy refinement. Online evaluation against SC2's built-in AI demonstrates consistent improvements, yielding win-rate gains of 30%, 15%, and 30% against Hard (LV5), Harder (LV6), and VeryHard (LV7), respectively, alongside improved macro-management stability and tactical risk assessment.

翻译：大型语言模型（LLM）近期展现出强大的推理与泛化能力，这促使研究者将其作为复杂环境中的决策策略进行探索。星际争霸II（SC2）因其庞大的状态-动作空间与部分可观测性，成为一个极具挑战性的测试平台。然而，现有基于LLM的SC2智能体主要聚焦于策略本身的改进，忽视了将可学习的、动作驱动的转移模型整合到决策循环中。为弥补这一空白，我们提出了StarWM——首个面向SC2的世界模型，能够在部分可观测条件下预测未来观测状态。为有效学习SC2的混合动态特性，我们设计了一种结构化文本表示方法，将观测状态分解为五个语义模块，并构建了首个用于SC2动态预测的指令微调数据集SC2-Dynamics-50k。我们进一步开发了面向结构化观测预测的多维度离线评估框架。离线实验结果表明，StarWM相比零样本基线模型取得显著提升，其中资源预测准确率提升近60%，己方宏观态势一致性亦大幅改善。最后，我们提出了StarWM-Agent——一个基于世界模型增强的决策系统，该系统将StarWM整合到"生成-模拟-优化"的决策循环中，实现前瞻驱动的策略优化。针对SC2内置AI的在线评估显示，该系统在Hard（LV5）、Harder（LV6）和VeryHard（LV7）难度下分别取得30%、15%和30%的胜率提升，同时展现出更稳定的宏观运营能力与更精准的战术风险评估。