LLM-PySC2：面向大型语言模型的星际争霸II学习环境
LLM-PySC2: Starcraft II learning environment for Large Language Models
AI总结：
针对LLM无法接入pysc2动作空间及缺乏多智能体协作支持的问题，提出了LLM-PySC2环境，提供完整动作空间与多模态信息，并验证了LLM在星际争霸II复杂场景下的决策潜力与局限。
摘要：
大型语言模型（LLMs）在智能决策问题中展现出了巨大潜力，在从游戏AI系统到复杂战略规划框架的各类应用中均表现出前所未有的能力。然而，过去十年来被广泛用于验证决策算法的星际争霸II平台，尚未为这一新兴领域提供实质性支持。为了解决LLM无法与pysc2后端的数百个动作接口对接，以及缺乏对多智能体（MA）协作原生支持的问题，我们提出了LLM-PySC2环境。这是首个为LLM提供完整pysc2动作空间、充足多模态信息及游戏Wiki知识的环境。借助异步查询架构，该环境能与LLM高效交互，且无论智能体数量规模如何，均能保持恒定的延迟。在实验中，我们评估了LLM在宏观决策和微观操作场景下的决策性能，测试采用了传统的星际争霸II多智能体挑战（SMAC）任务以及一系列新提出的任务。结果表明，LLM在复杂场景中具备取得胜利的潜力，但无法持续生成正确的决策，尤其是在恢复的pysc2动作空间和MA设置中。在缺乏与任务相关的指令时，预训练模型会出现幻觉和协作效率低下等问题。我们的研究结果表明，在大型模型时代，星际争霸II仍面临挑战，这表明要开发先进的LLM决策系统仍有许多工作要做，而所提出的LLM-PySC2环境将支持未来基于LLM的决策解决方案的开发。
英文摘要：
The tremendous potential has been demonstrated by large language models (LLMs) in intelligent decision-making problems, with unprecedented capabilities shown across diverse applications ranging from gaming AI systems to complex strategic planning frameworks. However, the StarCraft II platform, which has been widely adopted for validating decision-making algorithms in the past decade, has not yet provided substantial support for this emerging domain. To address issues that LLMs cannot interface with the hundreds of actions of the pysc2 backend and the lack of native support for multi-agent (MA) collaboration, we propose the LLM-PySC2 environment. This is the first environment that offers LLMs the complete pysc2 action space with sufficient multi-modal information and game Wiki knowledge. With an asynchronous query architecture, the environment efficiently interacts with LLMs that maintain a constant latency regardless of the scale of the agents' population. In the experiments, we evaluated LLMs' decision-making performance in both the macro-decision and micro-operation scenarios, with traditional StarCraft II Multi-Agent Challenge (SMAC) tasks and a series of new proposed. Results indicate that LLMs possess the potential to achieve victories in complex scenarios but cannot constantly generate correct decisions, especially in the recovered pysc2 action space and MA settings. Without task-relevant instructions, the pre-trained models suffer from issues such as hallucinations and inefficient collaboration. Our findings suggest that StarCraft II still challenges in the era of large models, revealing that there is a lot to do to develop an advanced LLM decision-making system, and the proposed LLM-PySC2 environment will support future development of LLM-based decision-making solutions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
