Kitti Puritat

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.

Gender-based restrictions in sacred heritage spaces challenge inclusive urban tourism planning. This study examines digital access at the Silver Ubosot in Chiang Mai, Thailand, where women cannot enter the sacred interior. An on-site quasi-experiment with 135 first-time female visitors compared VR360, immersive virtual reality (iVR), and AI-driven iVR. Compared with VR360, both immersive approaches were associated with significantly higher presence, engagement, and perceived substitution, but AI-iVR did not significantly outperform iVR. Substitution scores remained below the scale midpoint across conditions, indicating limited acceptance of virtual experiences as replacements for physical visitation. Visit intention did not differ significantly between groups. Parallel mediation analysis identified significant direct effects of both immersive approaches on substitution, but no significant indirect effects through presence or engagement. Greater immersion therefore does not necessarily make virtual access an adequate substitute for physical visitation. Digital access should be selected according to visitor needs, cultural protocols, interpretive goals, and operational capacity rather than technological sophistication alone. Less resource-intensive approaches may offer a practical option for providing digital access, while the additional benefits of AI-supported systems require further evaluation. Overall, digital access offers a complementary approach to experiencing restricted sacred heritage rather than a replacement for physical visitation.

Cultural heritage interpretation requires communicating relationships among physical locations, historical narratives, and symbolic meanings while accommodating diverse visitor information needs. Conversational artificial intelligence (AI) enables flexible, visitor-initiated access to cultural knowledge, but conversational interfaces alone provide limited spatial grounding. This study proposes an AI-supported interactive framework that combines conversational AI and projection mapping as complementary mechanisms within a unified heritage experience. Conversational AI supports semantic inquiry, while projection mapping spatially connects curated narratives with corresponding locations on a physical heritage model. The framework was implemented through the Seven Sacred Weeks Interactive Projection Mapping System at Wat Ched Yod, Thailand, with four modes: Tour, AI Conversation, Game, and Exploration. A mixed-methods pilot evaluation was conducted with 90 university students using pre- and post-test knowledge assessments, the System Usability Scale (SUS), and open-ended questions. Immediate post-test knowledge scores were significantly higher than pre-test scores following exposure to the complete system (p < 0.001; Cohen’s d = 1.416), and the system achieved a SUS score of 78. Qualitative findings highlighted spatial visualization, interactive activities, game-based interaction, and AI-supported inquiry, while limitations concerned waiting time, participation capacity, and AI response speed. The findings provide preliminary evidence of the feasibility and usability of coordinating technically distinct but complementary AI and spatial media mechanisms within a visitor-centered cultural heritage experience.

Introduction: Extended reality (XR), including virtual reality (VR) and mixed reality (MR), is increasingly used for training complex skills. However, the comparative effects of different interaction modalities under controlled conditions remain unclear, particularly regarding learning, task performance, and user experience. Methods: A controlled experiment compared PC, VR, and MR within a simulation‐based esports production training system. Ninety participants completed identical tasks. Outcome measures included knowledge gain, task performance, user engagement (UES‐SF), system usability (SUS), and cognitive workload (NASA‐TLX). Results: All conditions showed significant knowledge improvement, with no significant differences across groups. VR and MR yielded higher engagement, while VR was associated with higher cognitive workload. No significant differences were found in completion scores; however, immersive conditions (VR and MR) produced significantly lower error rates than PC. PC achieved the highest usability scores. Discussion: Training effectiveness depends on aligning interaction modality with instructional goals rather than immersion alone. VR was associated with lower error frequency during procedural tasks, MR offered a balanced performance–usability profile, and PC favored usability and lower workload. These findings provide practical guidance for selecting XR modalities in esports production training and support the design of context-appropriate digital training environments for workforce skill development and sustainable learning innovation.

Personalised three-dimensional (3D) facial avatars underpin a wide range of immersive virtual, augmented, and mixed reality (XR) experiences, yet conventional 3D capture pipelines remain prohibitively expensive and computationally demanding for prototype-stage XR applications. This study presents and evaluates a lightweight hybrid 3D Morphable Model–Convolutional Neural Network (3DMM-CNN) pipeline that reconstructs an animation-ready 3D facial mesh from a single unconstrained RGB photograph and exposes it through an interactive prototype with native export to XR-ready asset formats. A four-channel ResNet-50 backbone fuses RGB pixels with a landmark-mask channel, regresses the 3DMM shape, expression, pose, and illumination parameters, and is refined through a multi-task loss that combines 3D parameter regression, 2D landmark consistency, and image-to-mesh-to-image cycle consistency. The model is trained on a curated 2000-image subset of the LFW-People corpus and evaluated under four yaw-angle strata. The results indicate that on a held-out 400-image test set, the pipeline attains R² = 0.854, MSE = 0.022, Pearson r = 0.92, and MAPE = 10.6%, with a single-frame inference latency of 35 ms on a commodity RTX-class GPU. Robustness to head rotation improves by 29.9% at extreme poses (60–90° yaw) compared with a single-modality baseline. A Blender-integrated prototype successfully exports the reconstructed mesh as a deformation-ready asset for Unity- and Unreal-based XR engines. The proposed pipeline offers a cost-effective, real-time-capable component for XR avatar prototyping, lowering the entry barrier for small studios, immersive-learning developers, and AR/MR telepresence research. On the standard AFLW2000-3D benchmark, the pipeline additionally attains a Normalised Mean Error of 2.47% and a full-vertex reconstruction error of 1.50%, which is competitive with published lightweight baselines while retaining sub-50 ms inference latency.

This paper presents a workflow-driven VR simulation system for esports event production, designed to enable interaction with core production subsystems, including lighting control, audio management, and broadcast monitoring, within a task-based virtual environment that integrates spatial fidelity, workflow structure, and real-time feedback. A controlled pretest–posttest experiment with 80 undergraduate participants was conducted to evaluate the system in comparison with lecture-based instruction. The results indicate that while both approaches produced comparable gains in conceptual knowledge, the VR-based simulation led to significantly greater improvements in applied operational understanding and higher levels of user engagement. Interaction analytics further show that increased task complexity is associated with higher interaction frequency and lower completion rates, reflecting a trade-off between interaction fidelity and usability. These findings suggest that the effectiveness of VR-based simulation lies in its capacity to support scenario-based operational reasoning rather than conceptual learning alone, contributing to the design of virtual environments for complex workflow-based training.

The rapid proliferation of misinformation on social media underscores the urgent need for scalable digital-literacy instruction. This study presents the design and evaluation of a Generative AI-enhanced serious game system that integrates Large Language Models (LLMs) to drive adaptive non-player characters (NPCs). Unlike traditional scripted interactions, the system employs role-based prompt engineering to align real-time AI dialogue with the Currency, Relevance, Authority, Accuracy, and Purpose (CRAAP) framework, enabling dynamic scaffolding and authentic misinformation scenarios. A mixed-method experiment with 60 undergraduate students compared this AI-driven approach to traditional instruction using a 40-item digital-literacy pre/post test, the Intrinsic Motivation Inventory (IMI), and open-ended reflections. Results indicated that while both groups improved significantly, the game-based group achieved larger gains in credibility-evaluation performance and reported higher perceived competence, interest, and effort. Qualitative analysis highlighted the HCI trade-off between the high pedagogical value of adaptive AI guidance and technical constraints such as system latency. The findings demonstrate that Generative AI can be effectively operationalized as a dynamic interface layer in serious games to strengthen critical reasoning. This study provides practical guidelines for architecting AI-NPC interactions and advances the theoretical understanding of AI-supported educational informatics.

Pragmatic language is a core component of school-based social participation, yet children with Autism Spectrum Disorder (ASD) and Social Communication Disorder (SCD) frequently experience persistent difficulties in using language appropriately across everyday learning contexts. This study investigated the effectiveness of a culturally adapted, school-based immersive Virtual Reality (VR) learning program designed to enhance pragmatic language and social communication skills among Thai primary school children. Eleven participants aged 7–12 years completed a three-week, ten-session VR program that simulated authentic classroom, playground, and canteen interactions aligned with Thai sociocultural norms. Outcomes were measured using the Social Communication Questionnaire (SCQ) and the Pragmatic Behavior Observation Checklist (PBOC). While SCQ scores showed a small, non-significant reduction (p = 0.092), PBOC results demonstrated significant improvements in three foundational pragmatic domains: Initiation and Responsiveness (p = 0.032), Turn-Taking and Conversational Flow (p = 0.037), and Politeness and Register (p = 0.010). Other domains showed no significant changes. These findings suggest that immersive, culturally relevant VR environments can support early gains in core pragmatic language behaviors within educational settings, although broader social communication outcomes may require longer or more intensive learning experiences.

The Wua-Lai silvercraft community in Chiang Mai is experiencing a widening disconnect with younger visitors, raising concerns about the erosion of intangible cultural heritage. This study evaluates “Silver Craft Journey,” a location-based augmented reality (LBAR) system designed to revitalize cultural engagement and enhance cultural-heritage experience through context-aware, gamified exploration. A quasi-experimental field study with 254 participants across three age groups examined the system’s impact on cultural-heritage experience, knowledge acquisition, and real-world engagement. Results demonstrate substantial knowledge gains, with a mean increase of 7.74 points (SD = 4.37) and a large effect size (Cohen’s d = 1.77), supporting the effectiveness of LBAR in supporting tangible and intangible heritage understanding. Behavioral log data reveal clear age-related engagement patterns: older participants (41–51) showed declining mission completion rates and reduced interaction times at later points of interest, which may reflect increased cognitive and physical demands during extended AR navigation under real-world conditions. These findings underscore the potential of location-based AR to enhance cultural-heritage experience in real-world settings while highlighting the importance of age-adaptive interaction and route-design strategies. The study contributes a replicable model for integrating digital tourism, embodied AR experience, and community-based heritage preservation.