ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2404.02039
225
57
v1v2 (latest)

A Survey on Large Language Model-Based Game Agents

2 April 2024
Sihao Hu
Tiansheng Huang
Gaowen Liu
Ramana Rao Kompella
Gaowen Liu
Selim Furkan Tekin
Yichang Xu
    LLMAGLM&RoAI4CELM&MA
ArXiv (abs)PDFHTML
Abstract

The development of game agents holds a critical role in advancing towards Artificial General Intelligence (AGI). The progress of LLMs and their multimodal counterparts (MLLMs) offers an unprecedented opportunity to evolve and empower game agents with human-like decision-making capabilities in complex computer game environments. This paper provides a comprehensive overview of LLM-based game agents from a holistic viewpoint. First, we introduce the conceptual architecture of LLM-based game agents, centered around six essential functional components: perception, memory, thinking, role-playing, action, and learning. Second, we survey existing representative LLM-based game agents documented in the literature with respect to methodologies and adaptation agility across six genres of games, including adventure, communication, competition, cooperation, simulation, and crafting & exploration games. Finally, we present an outlook of future research and development directions in this burgeoning field. A curated list of relevant papers is maintained and made accessible at: this https URL.

View on arXiv
@article{hu2025_2404.02039,
  title={ A Survey on Large Language Model-Based Game Agents },
  author={ Sihao Hu and Tiansheng Huang and Gaowen Liu and Ramana Rao Kompella and Fatih Ilhan and Selim Furkan Tekin and Yichang Xu and Zachary Yahn and Ling Liu },
  journal={arXiv preprint arXiv:2404.02039},
  year={ 2025 }
}
Comments on this paper