Goal-Oriented Interactions in Games Using LLMs
IEEE Transactions on Games · 2025-06 · 17 (2) · 510-521
DOI: 10.1109/tg.2024.3515807 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Games, 2025-06. Verfasst von Adon Phillips und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 73 Literaturangaben. Gefördert von: Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
Unrealistic parser-based dialogue systems limit player agency. Large language model (LLM) characters can enhance agency but lack structure and measurable objectives. In this article, we propose a framework for structured interactions that tracks player progress through specific objectives, while also improving character LLM responses. This approach frames interactions as puzzles with states representing goal-based milestones. We employ an LLM to analyze dialogue history and enforce state transitions for state awareness and to enable specific actions like tailored LLM prompts and multimodal content changes. This results in a robust dialogue state tracking system for goal-based interactions. Using our method, a designer can craft transition rules as abstract goals that allow players to invent their own solutions rather than discovering the designer's intent. We demonstrate this with a hostage scenario game, where the player negotiates with a hostage-taker adversary. The game's effectiveness is assessed through qualitative gameplay analysis and a quantitative evaluation of our state tracking method.
Förderung
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Phillips, A., Lang, J., & Mould, D. (2025). Goal-Oriented Interactions in Games Using LLMs. IEEE Transactions on Games, 17(2), 510-521. https://doi.org/10.1109/tg.2024.3515807
Vancouver
Phillips A, Lang J, Mould D. Goal-Oriented Interactions in Games Using LLMs. IEEE Transactions on Games. 2025;17(2):510-521. doi:10.1109/tg.2024.3515807
BibTeX
@article{Phillips2025,
author = {Phillips, Adon and Lang, Jochen and Mould, David},
title = {Goal-Oriented Interactions in Games Using LLMs},
journal = {IEEE Transactions on Games},
year = {2025},
volume = {17},
number = {2},
pages = {510--521},
doi = {10.1109/tg.2024.3515807}
}
EUVIMED