【NICOGRAPH International2026】Lottery and Sprint Arcade

Slide used at NICOGRAPH International2026 oral presentation.
Title, "Lottery and Sprint Arcade: Enabling Player-Driven Game Editing with Generative AI"

Transcript

1. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group Maya Grace Torii 1), Takahito Murakami 1), Yoichi Ochiai 2) Lottery and Sprint Arcade: Enabling Player-Driven Game Editing with Generative AI 1 1) Graduate School of Comprehensive Human Sciences, University of Tsukuba 2) R & D Centre for Digital Nature, University of Tsukuba
2. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group Take away 2 🎙 Voice-Driven 🗣 Natural-language commands 🎮 In-Play Editing 🛠 Modify while playing 🆙 Instant Updates 🤖 Immediate AI response 🤾 Player Experience 🫀 Behavior & UX insights 📚 Over 100 configuration 🎖 Lottery and Sprint 🕹 Old Arcade 👾 Invader like
3. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group Background: From Offline Automation to Play-Driven Modification 3 Gallotta et al. [9] Miralvand et al. [4] Smith et al. [11] Offline Automation —-> Interactive Co-creation Jennings et al. [12] Charity et al. [6]
4. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group Background: Our Previous Work 4 Torii and Murakami et al. [11] Lottery and Sprint
5. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group Background: Extending Lottery and Sprint to Video Games 5 Too long —->
6. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group RQ1 How do users interact with and experience play-driven AI-mediated game editing? In other words, can users effectively modify a game through voice interaction, and how do they perceive the experience? Research Questions 6 RQ2 How do different editing patterns relate to player experience?
7. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group System Implementation: Hardware & Interface 7 GPT-4o Whisper Arcade1Up cabinet Microphone Raspberry Pi 5 Added Action Buttons
8. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group System Implementation: Parameters & The Play Loop 8 100+ Json Config Example In-play editing —-> w/ Natural Language, Voice and Cheatsheets
9. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group LLM Configuration Pipeline: Plan & Action 9 Use Voice Instruction w/ Cheatsheet
10. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group User Study 10 RQ1 How do users interact with and experience play-driven AI-mediated game editing? In other words, can users effectively modify a game through voice interaction, and how do they perceive the experience? RQ2 How do different editing patterns relate to player experience?
11. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group User Study Design 11 —-> NASA-TLX / UEQ / Post Survey(Original) —-> Editing Logs Analysis / PCA / Qualitative Analysis N = 21 5 gameplay-editing trials requiring at least 2 successful edits per trial Experimental Strategy RQ1 How do users interact with and experience play-driven AI-mediated game editing? In other words, can users effectively modify a game through voice interaction, and how do they perceive the experience? RQ2 How do different editing patterns relate to player experience?
12. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group Results RQ1: How did users experience play-driven game editing? 12 Reliable Pipeline: 97.1% success rate. Positive Experience (Easy and natural interaction) Accessible to Non-Experts (No significant differences) Key Findings
13. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group Results RQ2: What editing patterns emerged? 13 Log Analysis: Extracted via PCA. PC1 (Focus): Presentation vs. Interaction. PC2 (Depth): Immediate vs. Deeper changes. Key Findings
14. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group Results RQ2: Editing Patterns and Experience 14 Perceptible Edits ➔ Higher Usability Structural Edits ➔ Higher Enjoyment Key Insight: Styles shape the UX Key Findings
15. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group Results RQ2: Qualitative Findings 15 • “I was able to find fun in the unexpectedness.” (P16, None-EX) • “Seeing the unpredictable changes.” (P5, Amateur) • “[It felt like] creating my own new game.” (P16, None-EX) • Constraint awareness: Noted difficulty in adding entirely new mechanics beyond existing parameters (P20, P21, Pro). • Boundary testing: Used extreme values to understand system robustness and limits (P6, Pro). • Practical utility: Framed as a tool for fine-tuning development variables (P20, Pro). 2. Structural Editing 1. Exploratory Editing 3. Iterative Tuning Testing system affordances without fixed expectations. Transforming gameplay toward specific goals (e.g., bullet-hell, psychedelic). Systematically adjusting parameters to refine mechanics.
16. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group Discussion: Human-AI Co-Creation Dynamics 16 Accessible to All (RQ1) • Positive experiences and moderate workload across all skill levels. • Voice-based editing effectively may lowers the barrier to entry. Goal-Driven Collaboration (RQ2) • Diverse editing strategies emerge (Exploratory, Structural, Iterative) depending on user intent. Core Implication • Play-driven editing is a highly effective framework for real-time Human-AI Co-Creation.
17. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group Conclusion and Future Work 17 Conclusion • System: Developed Lottery & Sprint Arcade for real-time, voice-driven game editing. • Accessibility: Participants successfully edited games with positive experiences across experience levels. • Co-Creation: Multiple editing strategies emerged, highlighting the potential of play-driven editing. Future Work • Explore more complex game genres and richer rule systems. • Investigate how users perceive the role of AI during the creative process. • Study human-AI collaboration in longer-term creative activities.
18. Lottery and Sprint Arcade Torii et al. NICOGRAPH International 2026, Nagoya. University of Tsukuba, Digital Nature Group University of Tsukuba, Digital Nature Group [1] Noor Shaker, Julian Togelius, and Mark J Nelson. Procedural content generation in games. 2016. [2] Eric Piette, Dennis JNJ Soemers, Matthew Stephenson, Chiara F Sironi, Mark HM Winands, and Cameron Browne. Ludii–the ludemic general game system. arXiv preprint arXiv:1905.05013, 2019. [3] Mahdi Farrokhi Maleki and Richard Zhao. Procedural content generation in games: A survey with insights on emerging llm integration. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 20, pages 167–178, 2024. [4] Hamid Zand Miralvand, Mohammad Ronagh Nikghalb, Mohammad Darandeh, Abidullah Khan, Ian Arawjo, and Jinghui Cheng. Democratizing game modding with genai: A case study of starcharm, a stardew valley character maker. Proceedings of the ACM on Human-Computer Interaction, 9(6):475–509, 2025. [5] Shyam Sudhakaran, Miguel Gonz´alezDuque, Matthias Freiberger, Claire Glanois, Elias Najarro, and Sebastian Risi. Mariogpt: Open-ended text2level generation through large language models. Advances in Neural Information Processing Systems, 36:54213–54227, 2023. [6] Megan Charity, Ahmed Khalifa, and Julian Togelius. Baba is y’ all: Collaborative mixedinitiative level design. In 2020 IEEE Conference on Games (CoG), pages 542–549. IEEE, 2020. [7] Maya Grace Torii, Takahito Murakami, and Yoichi Ochiai. Lottery and sprint: Generate a board game with design sprint method on autogpt. In Companion Proceedings of the Annual Symposium on ComputerHuman Interaction in Play, pages 259–265, 2023. [8] Graham Todd, Sam Earle, Muhammad Umair Nasir, Michael Cerny Green, and Julian Togelius. GAVEL: Generating games via evolution and language models. In Advances in Neural Information Processing Systems, volume 37, 2024. [9] Roberto Gallotta and Antonios Liapis. Consistent game content creation via function calling for large language models. In Proceedings of the IEEE Conference on Games (CoG), 2024. [10] Jim Whitehead, Nathan Sturtevant, and Rachel Harber. Conversational interactions with procedural generators using large language models. In Proceedings of the Foundations of Digital Games (FDG), 2025. [11] Gillian Smith, Jim Whitehead, and Michael Mateas. Tanagra: A mixed-initiative level design tool. In Proceedings of the International Conference on the Foundations of Digital Games (FDG), pages 209–216, 2010. [12] Martin Jennings-Teats, Michael Mateas, and Noah Wardrip-Fruin. What’s the game, then? opportunities and challenges for runtime behavior generation. In Proceedings of the ACM Symposium on User Interface Software and Technology (UIST), 2024. [13] Riemer van Rozen. Live game design: Prototyping at the speed of play. In Proceedings of the Foundations of Digital Games (FDG), 2025. [14] David Oswald, Matthias Roth, Fabio Z¨und, Roger M¨ori, Bob Sumner, and Markus Gross. The real augmented reality: Realtime game editor in a spatial augmented environment. In Proceedings of the International Conference on Advances in Computer Entertainment Technology (ACE), 2014. [15] Ellen Jiang, Kristen Olson, Edwin Toh, Alejandra Molina, Aaron Donsbach, Michael Terry, and Carrie J Cai. ”what it wants me to say”: Bridging the abstraction gap between end-user programmers and codegenerating LLMs. In Proceedings of the CHI Conference on Human Factors in Computing Systems. ACM, 2022. [16] J.D. Zamfirescu-Pereira and Qian Yang Tian, Bjoern Hartmann. How humans communicate programming tasks to AI assistants and implications for end-user programming with LLMs. In Proceedings of the CHI Conference on Human Factors in Computing Systems. ACM, 2024. [17] Shreeya Panchanadikar and Guo Freeman. ”i’m a solo developer but AI is my new ill-informed co-worker”: How indie game developers envision AI for creative workflows. Proceedings of the ACM on HumanComputer Interaction, 8(CHI PLAY), 2024. [18] Jonathan Liebers, Constantin Burschik, Menna Abdelaziz, Uwe Gruenefeld, and Stefan Schneegass. Computer, generate! investigating user-controlled generation of immersive virtual environments. Computers & Graphics, 123, 2024. [19] Matthew Guzdial, Nicholas Liao, and Mark Riedl. Friend, collaborator, student, manager: How design of an AI-driven game level editor a ects creators. In Proceedings of the CHI Conference on Human Factors in Computing Systems. ACM, 2019. [20] Caterina Moruzzi and Pedro Margarido. A user-centered framework for human-AI cocreativity. In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems. ACM, 2024. [21] Megan Charity and Julian Togelius. The ink splotch e ff ect: A case study on ChatGPT as a co-creative game designer. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE), 2023. [22] Megan Charity, Michael Cerny Green, and Julian Togelius. Language as reality: A cocreative storytelling game experience in 1001 nights using generative AI. In Proceedings of the IEEE Conference on Games (CoG), 2023. [23] Bettina Laugwitz, Theo Held, and Martin Schrepp. Construction and evaluation of a user experience questionnaire. In Symposium of the Austrian HCI and Usability Engineering Group (USAB), volume 5298 of Lecture Notes in Computer Science, pages 63–76, Berlin, Heidelberg, 2008. Springer. [24] Sandra G. Hart and Lowell E. Staveland. Development of NASA-TLX (Task Load Index): Results of empirical and theoretical research. In Peter A. Hancock and Najmedin Meshkati, editors, Human Mental Workload, pages 139–183. North-Holland, Amsterdam, 1988. [25] ๕լൟand ਫ্௚थ. ೔ຊޠ൛NASA-TLX ʹΑΔϝϯλϧϫʔΫϩʔυଌఆ. ਓؒ޻ֶ, 32(2):71–79, 1996. Bibliography 18