EUVIMEDEUVIMED entdecken
Crossref

Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees

Parsa Rahmati, Richard Zhao

Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · 08.11.2026 · 22 (1) · 160-169

DOI: 10.1609/aiide.v22i1.43574 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, online erschienen am 08.11.2026. Verfasst von Parsa Rahmati und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large Language Models (LLMs) enable open-ended dialogue in interactive games, but their non-deterministic outputs make it difficult to preserve authorial control, factual consistency, and the intended sequence of information disclosure. These challenges are particularly significant in detective games, where premature revelation or fabricated details can undermine the logic of player progression. We present a Structured Knowledge Tree architecture coupled with a tri-agent LLM pipeline for controlling dialogue in an open-ended interrogation game. The system separates knowledge retrieval, dialogue generation, and response verification to ensure that the virtual suspect reveals only information permitted by the current narrative state. We evaluate the approach through The Interrogation of Adrian Gale, a playable detective-game testbed, and a formal user study examining hallucination reduction, adherence to authored disclosure sequences, and perceived logical progression. Our results demonstrate that the structured architecture reduces critical hallucinations by 64.78% and entirely prevents premature narrative disclosure. While the strict mechanical constraints introduced usability trade-offs regarding forced conversational reveals, the system successfully enforces rigorous epistemic pacing and provides players with a clear, subjective sense of progression toward solving the case.

Zitieren

APA

Rahmati, P., & Zhao, R. (2026). Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 22(1), 160-169. https://doi.org/10.1609/aiide.v22i1.43574

Vancouver

Rahmati P, Zhao R. Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. 2026;22(1):160-169. doi:10.1609/aiide.v22i1.43574

BibTeX
@article{Rahmati2026,
  author = {Rahmati, Parsa and Zhao, Richard},
  title = {Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment},
  year = {2026},
  volume = {22},
  number = {1},
  pages = {160--169},
  doi = {10.1609/aiide.v22i1.43574}
}
Kostenlos starten →