Large language models (LLMs) offer promise for dynamic game content generation, but they face critical barriers, including narrative incoherence and high operational costs. Due to their large size, they are often accessed in the cloud, limiting their application in offline games. Many of these practical issues are solved by pivoting to small language models (SLMs), but existing studies using SLMs have resulted in poor output quality. We propose a strategy of achieving high-quality SLM generation through aggressive fine-tuning on deliberately scoped tasks with narrow context, constrained structure, or both. In short, more difficult tasks require narrower scope and higher specialization to the training corpus. Training data is synthetically generated via a DAG-based approach, grounding models in the specific game world. Such models can form the basis for agentic networks designed around the narratological framework at hand, representing a more practical and robust solution than cloud-dependent LLMs. To validate this approach, we present a proof-of-concept focusing on a single specialized SLM as the fundamental building block. We introduce a minimal RPG loop revolving around rhetorical battles of reputations, powered by this model. We demonstrate that a simple retry-until-success strategy reaches adequate quality (as defined by an LLM-as-a-judge scheme) with predictable latency suitable for real-time generation. While local quality assessment remains an open question, our results demonstrate feasibility for real-time generation under typical game engine constraints.

翻译：大型语言模型（LLM）为动态游戏内容生成提供了前景，但其面临叙事不连贯和高运营成本等关键障碍。由于模型规模庞大，它们通常部署在云端，这限制了其在离线游戏中的应用。通过转向小型语言模型（SLM）可解决许多此类实际问题，但现有使用SLM的研究往往导致输出质量低下。我们提出一种策略，通过对具有狭窄上下文、受限结构或两者兼具的精心限定任务进行积极微调，从而实现高质量的SLM生成。简言之，任务越复杂，所需的任务范围越窄，对训练语料的专业化程度要求越高。训练数据通过基于有向无环图（DAG）的方法合成生成，使模型植根于特定的游戏世界。此类模型可构成围绕现有叙事学框架设计的智能体网络的基础，相比依赖云端的LLM，这是一种更实用、更稳健的解决方案。为验证该方法，我们提出了一个概念验证，聚焦于将单一专业化SLM作为基础构建模块。我们引入了一个以该模型驱动的、围绕声誉修辞对战的最小化角色扮演游戏循环。实验表明，采用简单的“重试直至成功”策略可在可预测的延迟内达到足够质量（以LLM作为评判器的方案定义），适合实时生成。尽管本地质量评估仍是待解决的问题，但我们的结果证明了在典型游戏引擎约束下实现实时生成的可行性。