Thesis (Selection of subject)Thesis (Selection of subject)(version: 391)
Thesis details
   Login via CAS
Detektivní počítačová hra používající velké jazykové modely
Thesis title in Czech: Detektivní počítačová hra používající velké jazykové modely
Thesis title in English: A detective computer game utilizing large language models
Key words: velké jazykové modely|unreal engine 5
English key words: large language models|unreal engine 5
Academic year of topic announcement: 2024/2025
Thesis type: diploma thesis
Thesis language:
Department: Department of Software and Computer Science Education (32-KSVI)
Supervisor: Mgr. Vojtěch Černý
Author: hidden - assigned and confirmed by the Study Dept.
Date of registration: 19.11.2024
Date of assignment: 26.11.2024
Confirmed by Study dept. on: 15.04.2025
Guidelines
The objective of this master's thesis is to explore the integration of large language models (LLMs) to Unreal Engine 5 to create believable, human-like AI interactions. This aims to understand how LLMs can influence video games through realistic dialogues, immersive narratives, and emergent conversations. To achieve this goal, a simple detective game will be developed featuring AI agents capable of interacting with each other, behaving believably, perceiving their environment, and retaining memory to enhance user interactions.
References
Generative Agents: Interactive Simulacra of Human Behavior, Joon Sung Park and Joseph C. O'Brien and Carrie J. Cai and Meredith Ringel Morris and Percy Liang and Michael S. Bernstein, https://arxiv.org/abs/2304.03442
A Trainable Agent for Role-Playing, Yunfan Shao and Linyang Li and Junqi Dai and Xipeng Qiu, https://arxiv.org/abs/2310.10158
Study on using language models in storytelling games, Jiří Macháček, http://hdl.handle.net/10467/114665
P. Taveekitworachai, K. Plupattanakit and R. Thawonmas, "Assessing Inherent Biases Following Prompt Compression of Large Language Models for Game Story Generation," 2024 IEEE Conference on Games (CoG), https://ieeexplore.ieee.org/document/10645609
Yang, Daijin & Kleinman, Erica & Harteveld, Casper. (2024). GPT for Games: An Updated Scoping Review (2020-2024), https://www.researchgate.net/publication/385510765_GPT_for_Games_An_Updated_Scoping_Review_2020-2024
 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html