PulseAugur
EN
LIVE 07:48:21

LLM-based NPCs in Video Games: A Systematic Mapping Study

By PulseAugur Editorial · [1 sources] ·

A systematic mapping study analyzed 377 papers to understand the current state of large language model (LLM) integration into video game non-player characters (NPCs). The research found that while LLMs offer the potential for more dynamic and adaptive NPCs, widespread adoption of advanced features like long-term memory and retrieval-augmented generation is limited. The study also quantified adoption rates for various components, noted response times ranging from 2.6 to 15 seconds, and identified six key barriers to commercial implementation, offering recommendations for future development. AI

IMPACT Provides a structured overview of LLM integration in video game NPCs, highlighting adoption rates and barriers for developers and researchers.

RANK_REASON The cluster is a systematic mapping study published on arXiv, analyzing academic literature on a specific application of AI. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

LLM-based NPCs in Video Games: A Systematic Mapping Study

How we ranked this

Signal score
27 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster is a systematic mapping study published on arXiv, analyzing academic literature on a specific application of AI. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Dilan Mian, Jeremy Bradbury, Yann-Ga\"el Gu\'eh\'eneuc, Fabio Petrillo, Cristiano Politowski ·

    LLM-based NPCs in Video Games: A Systematic Mapping Study

    arXiv:2611.05427v1 Announce Type: cross 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 situat…

RELATED ENTITIES

RELATED TOPICS