arXiv cs.AI· Dilan Mian, Jeremy Bradbury, Yann-Ga\"el Gu\'eh\'eneuc, Fabio Petrillo, Cristiano Politowski·· 3 小时前AI 评分46
基于 LLM 的游戏 NPC：系统性映射研究
LLM-based NPCs in Video Games: A Systematic Mapping Study
AI 导读
一项系统性映射研究分析了学术文献中 377 篇论文，最终对 42 篇论文围绕大语言模型驱动的游戏 NPC 展开系统梳理，涵盖四个主题轴及十个子问题。研究首次定量刻画了组件采用率、延迟、安全覆盖与可复现性：短期记忆和世界状态接地接近普及（60% 与 69%），而长期记忆（31%）、反思（38%）和 RAG（14%）仍少见，响应时间为 2.6 至 15 秒。
正文 · 原文
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, and at what cost. We address this gap with a systematic mapping study of 377 papers from the academic literature, yielding 42 papers analysed against a main research question and ten sub-questions across four thematic axes. We provide the first quantitative characterisation of component adoption, latency, safety coverage, and reproducibility: short-term memory and world-state grounding are near-universal (60% and 69%), whereas long-term memory (31%), reflection (38%), and retrieval-augmented generation (14%) remain rare, and response times span 2.6 to 15 seconds. Finally, we identify six structural barriers to commercial adoption and offer evidence-based recommendations for developers and researchers.
| Comments: | 12 pages. Accepted manuscript. Published in IEEE Transactions on Games (Early Access) |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.05427 [cs.SE] |
| (or arXiv:2611.05427v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05427 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1109/TG.2026.3733302
DOI(s) linking to related resources |
Submission history
From: Dilan Mian [view email]
[v1]
Mon, 2 Nov 2026 23:03:44 UTC (68 KB)
来源：arXiv cs.AI · arxiv.org