用大模型把故事变2D游戏关卡，自动匹配物体与场景
Narrative-to-Scene Generation: An LLM-Driven Pipeline for 2D Game Environments
- 分三时态提取故事中的对象关系三元组
- 基于语义嵌入检索游戏素材，用细胞自动机生成地形
- 适合做叙事驱动的自动化游戏关卡生成研究
大型语言模型（LLMs）可生成精彩故事，但将文本叙事转化为可玩的视觉环境仍是程序化内容生成（PCG）中的开放挑战。本文提出一种轻量级流程，将简短叙事提示转换为一系列反映故事时间结构的2D瓦片化游戏场景。给定由LLM生成的叙事，系统识别三个关键时间帧，提取以“对象-关系-对象”形式存在的空间谓词，并利用来自GameTileNet数据集的具身感知语义嵌入检索视觉资产。通过细胞自动机生成分层地形，再根据谓词结构中的空间规则放置物体。我们在十个不同故事上评估了该系统，分析了瓦片-物体匹配度、具身层对齐情况以及空间约束满足程度。此原型提供了一种可扩展的叙事驱动场景生成方法，为未来在故事中心的PCG中实现多帧连续性、符号追踪和多智能体协作奠定了基础。
原文摘要 · Abstract (English)
Recent advances in large language models (LLMs) enable compelling story generation, but connecting narrative text to playable visual environments remains an open challenge in procedural content generation (PCG). We present a lightweight pipeline that transforms short narrative prompts into a sequence of 2D tile-based game scenes, reflecting the temporal structure of stories. Given an LLM-generated narrative, our system identifies three key time frames, extracts spatial predicates in the form of "Object-Relation-Object" triples, and retrieves visual assets using affordance-aware semantic embeddings from the GameTileNet dataset. A layered terrain is generated using Cellular Automata, and objects are placed using spatial rules grounded in the predicate structure. We evaluated our system in ten diverse stories, analyzing tile-object matching, affordance-layer alignment, and spatial constraint satisfaction across frames. This prototype offers a scalable approach to narrative-driven scene generation and lays the foundation for future work on multi-frame continuity, symbolic tracking, and multi-agent coordination in story-centered PCG.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。