This study examines NPC dialogue mechanisms as an independent design factor in task-oriented digital games. Although generative NPCs are often discussed in relation to narrative richness, conversational naturalness, and social presence, limited controlled evidence exists on whether dialogue mechanisms themselves affect player outcomes when task information is held constant. To address this gap, the study combined a formative user study with a single-factor between-subject experiment using a controlled game prototype. The LLM-NPC and Script NPC conditions shared identical task goals, scene structure, completion criteria, predefined fact set, and task-stage prompting boundaries. The experimental contrast was therefore framed as a comparison between a script-based branching dialogue interface and a boundary-controlled LLM-based adaptive dialogue interface, rather than as a comparison involving unequal task information. The results showed that, under controlled information boundaries, LLM-NPCs significantly improved task efficiency, as reflected in shorter completion time, fewer NPC inquiries, and fewer incorrect searches. For immersion, the overall multivariate effect was not statistically significant, and no confirmatory evidence of an LLM-NPC advantage in immersion was found. For satisfaction, the LLM-NPC condition showed significantly higher total satisfaction, which was specified as the primary satisfaction endpoint. Secondary affective and overall evaluative satisfaction outcomes showed consistent uncorrected differences in the same direction. These findings suggest that, under the implemented factual and procedural controls, the value of LLM-NPCs in this task-oriented setting is less likely to lie in providing more information than in reorganizing predefined task facts in a more context-sensitive and player-adaptive manner. Boundary-controlled adaptive dialogue may therefore provide a useful design perspective for future task-oriented NPC systems.
As generative artificial intelligence (GenAI) becomes increasingly embedded in university learning, AI-generated feedback offers more accessible and efficient support. However, its educational value depends on how students evaluate and process the feedback they receive. From the perspective of responsible use of AI-generated feedback, this study develops a capability–risk dual-path model linking Student Feedback Literacy (SFL) and Dependence on AI-Generated Feedback (AIFD) to self-reported Sustainable Learning Engagement (SLE) through Critical Engagement with AI-Generated Feedback (CEAF) and Uncritical Acceptance of AI-Generated Feedback (UAAF). Survey data from 368 Chinese university students were analyzed using structural equation modeling and bootstrap analysis of indirect associations. Higher SFL was associated with greater CEAF and lower UAAF, whereas higher AIFD showed the opposite pattern. CEAF was positively associated with SLE, while UAAF was negatively associated with SLE. Significant indirect associations with SLE were also observed through both feedback-processing pathways. These findings suggest that the educational implications of AI-generated feedback should be considered not only in terms of efficiency but also in terms of whether students remain actively involved in evaluating, reflecting on, and selectively using AI suggestions rather than becoming overly reliant on them.