基于LLM的视频游戏NPC：系统映射研究
原标题：LLM-based NPCs in Video Games: A Systematic Mapping Study
AI 摘要
该论文对377篇文献进行系统映射研究，最终筛选出42篇进行分析，首次定量刻画了基于LLM的NPC在组件采用、延迟、安全覆盖和可复现性方面的现状。研究发现短期记忆（60%）和世界状态 grounding（69%）几乎普遍采用，而长期记忆（31%）、反思（38%）和RAG（14%）仍属少数，端到端响应时间为2.6至15秒。论文还识别出商业化采用的六大结构性障碍，并为开发者和研究者提供基于证据的建议。
正文节选
LLM-based NPCs in Video Games: A Systematic Mapping Study Abstract For decades, non-player characters (NPCs) have been driven by rule-based systems whose personalities and interactions are scripted before release. Large language models (LLMs) promise NPCs that converse openly, adapt to new situations, and behave in ways developers did not fully author, prompting a wave of research and commercial experimentation. Yet the field lacks a unified picture of what has been built, how well it works, an