Recent advances in LLMs have enabled new possibilities for creative content generation, yet their use in game design is often limited by poor integration across creative components, particularly for novice designers aiming to rapidly prototype playable concepts. Guided by the Elemental Tetrad framework, we present RPGAgent, an LLM-driven multi-agent system specifically designed to assist novice game creators in transforming a short story outline into a playable game. Specialized agents exchange structured data to generate coherent narrative, scene, and gameplay mechanics, ensuring structural correctness and consistency between story and world. By combining LLM-based generation with procedural content creation, the system offers a controllable and interpretable workflow. In a within-subjects study with 18 participants, RPGAgent outperformed a GPT-assisted baseline in both user experience and creative satisfaction during the prototyping of playable RPGs. These results demonstrate the potential of collaborative multi-agent frameworks for structured, AI-assisted game design.

Beijing Swallow Kites, one of China’s most iconic traditional crafts, hold a significant place within the country’s intangible cultural heritage (ICH). However, with rapid modernization and urbanization, the transmission of traditional kite-making skills faces severe challenges, leading to a gradual decline. To address this, we developed KiteMR, an interactive Mixed Reality (MR) system that digitally recreates this craft, offering users an immersive kite-making experience. KiteMR combines physical and digital elements with AI-assisted design, storytelling, and gamification to enhance user engagement, allowing for the creation of personalized kites. A comparative evaluation with video-based methods revealed that KiteMR significantly increased user interest in ICH, deepened their cultural understanding, and fostered emotional connections through immersive interaction. This system not only preserves and disseminates traditional craftsmanship in a digital format but also inspires deeper cultural reflection and identity.

As generative artificial intelligence (AI) technologies continue to develop rapidly, this research focused on exploring the factors affecting users’ word-of-mouth (WOM) intentions of AI profile picture generation services. Specifically, a model was constructed based on the technology acceptance model (TAM), self-presentation theory, and perceived risk theory. Subsequently, the model was examined via the analysis of survey-based data from 312 Korean AI profile picture generation service users. The outcomes indicated that online self-presentation desire positively affected perceived usefulness (PU). Also, PU and perceived ease of use (PEU) were positively associated with attitude, which in turn positively affected the WOM intention. However, the effects of online self-presentation desire and perceived risk on attitude and the influence of PEU on PU are found to be insignificant. Consequently, this research is one of the first studies identifying factors affecting WOM intention of AI-profile generation services.

Osteoporotic vertebral compression fractures (OVCFs) are prevalent in the elderly population, typically assessed on computed tomography (CT) scans by evaluating vertebral height loss. This assessment helps determine the fracture's impact on spinal stability and the need for surgical intervention. However, the absence of pre-fracture CT scans and standardized vertebral references leads to measurement errors and inter-observer variability, while irregular compression patterns further challenge the precise grading of fracture severity. While deep learning methods have shown promise in aiding OVCFs screening, they often lack interpretability and sufficient sensitivity, limiting their clinical applicability. To address these challenges, we introduce a novel vertebra synthesis-height loss quantification-OVCFs grading framework. Our proposed model, HealthiVert-GAN, utilizes a coarse-to-fine synthesis network designed to generate pseudo-healthy vertebral images that simulate the pre-fracture state of fractured vertebrae. This model integrates three auxiliary modules that leverage the morphology and height information of adjacent healthy vertebrae to ensure anatomical consistency. Additionally, we introduce the Relative Height Loss of Vertebrae (RHLV) as a quantification metric, which divides each vertebra into three sections to measure height loss between pre-fracture and post-fracture states, followed by fracture severity classification using a Support Vector Machine (SVM). Our approach achieves state-of-the-art classification performance on both the Verse2019 dataset and in-house dataset, and it provides cross-sectional distribution maps of vertebral height loss. This practical tool enhances diagnostic accuracy in clinical settings and assisting in surgical decision-making.

Due to the tremendous growth in user population over online social networks (OSNs), interactive messaging traffic has experienced exponential growth, which consequently causes serious privacy concerns. Malicious users may utilize camouflage, phishing, and other unconventional social engineering techniques to lure ordinary users to reveal their sensitive attributes in their interactive messages when they least expect. In addition, during a communication session, attackers may intercept data packets with sensitive attributes to obtain private information. Therefore, it is of paramount importance for the system to successfully identify malicious users and prevent them from obtaining private information from messages containing sensitive attributes when socializing over OSNs. In this article, we propose a privacy-preserving scheme for interactive messaging by leveraging user credibility that characterizes users' reputation based on users' social behaviors and uses the item response theory in psychometrics to assess the risk levels of users' interactive messages. This scheme ensures the privacy preservation during message exchange through message obfuscation with the message replication and the replacement of sensitive attributes. Through the experiments on a Facebook-like Social Network Data Set, we have demonstrated that our proposed scheme has high availability and accuracy while achieving the high success rate to identify malicious users, which can thus greatly reduce the privacy leakage.

How humans achieve long-term goals in an uncertain environment, via repeated trials and noisy observations, is an important problem in cognitive science. We investigate this behavior in the context of a multi-armed bandit task. We compare human behavior to a variety of models that vary in their representational and computational complexity. Our result shows that subjects' choices, on a trial-to-trial basis, are best captured by a forgetful" Bayesian iterative learning model in combination with a partially myopic decision policy known as Knowledge Gradient. This model accounts for subjects' trial-by-trial choice better than a number of other previously proposed models, including optimal Bayesian learning and risk minimization, epsilon-greedy and win-stay-lose-shift. It has the added benefit of being closest in performance to the optimal Bayesian model than all the other heuristic models that have the same computational complexity (all are significantly less complex than the optimal model). These results constitute an advancement in the theoretical understanding of how humans negotiate the tension between exploration and exploitation in a noisy, imperfectly known environment."