Distributed Multi-Agent Generative AI for Information Verification: A Controlled Comparison of Single-Agent and Multi-Agent Serious Games
Technologies · 11.11.2026 · 14 (11) · 746
DOI: 10.3390/technologies14110746 ↗Kurz gefasst
Fachartikel in der Zeitschrift Technologies, online erschienen am 11.11.2026. Verfasst von Kannikar Intawong und 3 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chiang Mai University, Faculty of Humanities, Chiang Mai University.
Abstract (Originalsprache)
Generative-AI learning systems typically centralize conversational information in one agent or use multiple agents primarily as tutors or collaborators. This study presents a distributed multi-agent generative-AI architecture in which role-specific AI non-player characters (AI-NPCs) act as bounded information sources with private evidence states. The architecture was implemented in an information-verification serious game and evaluated with 90 first-year undergraduates randomly assigned to classroom instruction, a single-agent AI game, or a distributed multi-agent AI game. The two AI configurations used the same cases, total information, verification resources, GPT-5.1 model, generation settings, scoring rules, and final task; the principal difference was the information-access architecture and its associated interaction demands. All conditions produced substantial digital-literacy knowledge gains, with no significant differences in transfer accuracy. The multi-agent condition outperformed classroom instruction in source evaluation, evidence integration, and reasoning quality, and significantly exceeded the single-agent condition only in evidence integration. It also showed more frequent investigative actions. These findings suggest that controlled information distribution across generative-AI agents can influence information-seeking and evidence integration even when the underlying model and available information are held constant, supporting bounded agent states and controlled information asymmetry as interaction-design mechanisms for information verification.
Förderung
- Chiang Mai University
- Faculty of Humanities, Chiang Mai University
Zitieren
APA
Intawong, K., Yolthasart, S., Charoenkit, S., & Puritat, K. (2026). Distributed Multi-Agent Generative AI for Information Verification: A Controlled Comparison of Single-Agent and Multi-Agent Serious Games. Technologies, 14(11), 746. https://doi.org/10.3390/technologies14110746
Vancouver
Intawong K, Yolthasart S, Charoenkit S, Puritat K. Distributed Multi-Agent Generative AI for Information Verification: A Controlled Comparison of Single-Agent and Multi-Agent Serious Games. Technologies. 2026;14(11):746. doi:10.3390/technologies14110746
BibTeX
@article{Intawong2026,
author = {Intawong, Kannikar and Yolthasart, Suratchanee and Charoenkit, Suphakan and Puritat, Kitti},
title = {Distributed Multi-Agent Generative AI for Information Verification: A Controlled Comparison of Single-Agent and Multi-Agent Serious Games},
journal = {Technologies},
year = {2026},
volume = {14},
number = {11},
pages = {746},
doi = {10.3390/technologies14110746}
}
EUVIMED