Jiaxiang Zhao
Jiaxiang Zhao has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Yanzhen Li
Department of Smart Experience Design, Graduate School of Techno Design, Kookmin University, Seoul, Republic of Korea
2 shared publications - Jing Deng
Department of Visual and Media Design, Academy of Art & Design, Hunan Institute of Science and Technology, 439 Xiangbei Avenue, Yueyang 414000, China
1 shared publication - Jinho Yim
Department of Smart Experience Design, Graduate School of Techno Design, Kookmin University, Seoul 02707, Republic of Korea
1 shared publication - Jizhen Deng
Henan Kaifeng College of Science Technology and Communication, Kaifeng, Henan, China
1 shared publication
Latest Publications
- Open Access
- 20 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (14) , 7254
Comparing LLM-Driven and Script-Based Non-Player Characters Under Controlled Information Boundaries: Effects on Task Performance, Immersion, and Satisfaction
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.
- 20 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (14) , 7254
Open AccessComparing LLM-Driven and Script-Based Non-Player Characters Under Controlled Information Boundaries: Effects on Task Performance, Immersion, and Satisfaction
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.
- Open Access
- 27 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 370-374
Research on Optimizing AI-Assisted Film and Television VFX Production
- 27 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 370-374
Open AccessResearch on Optimizing AI-Assisted Film and Television VFX Production