EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SPARK_AI: A Prompt-Orchestrated Architecture for Stateful, Process-Oriented Reasoning with Large Language Models

Marija Kaplar, Sebastijan Kaplar, Miloš Vučić, Lidija Ivanović, Aleksandra Stevanović, Aleksandar Milenković, Nemanja Vučićević

Informatics · 17.04.2026 · 13 (4) · 63

DOI: 10.3390/informatics13040063 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Informatics, online erschienen am 17.04.2026. Verfasst von Marija Kaplar und 6 weiteren Autor:innen. Die Arbeit nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents SPARK_AI, a prompt-orchestrated system architecture for governing how large language models (LLMs) conduct structured and adaptive reasoning in human–AI interaction. The framework mitigates ad hoc LLM use by replacing direct answer generation with a process-oriented, step-by-step reasoning workflow. We focus on SPARK_AI_MATH, a domain module that supports learners in solving non-routine problem-solving tasks by operationalizing well-established problem-solving phases and guided questioning dialog strategies (Socratic-style prompts), with an optional tool-mediated visualization layer (e.g., GeoGebra). The module implements a five-phase conversational protocol consisting of problem interpretation, analysis of givens, planning, execution, and reflection, together with a controlled hint policy. This design is realized through a stateful system architecture in which each problem instance is maintained as an independent interaction track with a persistent reasoning state. User acceptance was evaluated by first-year mechanical engineering students (N = 108) using an expanded Technology Acceptance Model instrument, and the results were analyzed via PLS-SEM. The findings indicate overall favorable perceptions, with perceived usefulness and learning support emerging as key predictors of intention for continued use. Beyond this specific domain, the SPARK_AI framework enables efficient domain adaptation through localized prompt strategies while preserving a shared cognitive control layer for reasoning-centered human–LLM interaction.

Zitieren

APA

Kaplar, M., Kaplar, S., Vučić, M., Ivanović, L., Stevanović, A., Milenković, A., & Vučićević, N. (2026). SPARK_AI: A Prompt-Orchestrated Architecture for Stateful, Process-Oriented Reasoning with Large Language Models. Informatics, 13(4), 63. https://doi.org/10.3390/informatics13040063

Vancouver

Kaplar M, Kaplar S, Vučić M, Ivanović L, Stevanović A, Milenković A, et al. SPARK_AI: A Prompt-Orchestrated Architecture for Stateful, Process-Oriented Reasoning with Large Language Models. Informatics. 2026;13(4):63. doi:10.3390/informatics13040063

BibTeX
@article{Kaplar2026,
  author = {Kaplar, Marija and Kaplar, Sebastijan and Vučić, Miloš and Ivanović, Lidija and Stevanović, Aleksandra and Milenković, Aleksandar and Vučićević, Nemanja},
  title = {SPARK_AI: A Prompt-Orchestrated Architecture for Stateful, Process-Oriented Reasoning with Large Language Models},
  journal = {Informatics},
  year = {2026},
  volume = {13},
  number = {4},
  pages = {63},
  doi = {10.3390/informatics13040063}
}
Kostenlos starten →