Problem
Research questions and friction points this paper is trying to address.
AI-native games
multi-agent systems
generative AI
deck-building
tactical arena
"Pharos Night: Crown Pursuit": An AI-Native Deck-Building and Tactical Arena Game Design Based on Multi-Agent Systems
🤖 AI Summary
This work explores the design of native AI-driven games in which generative AI directly governs game rules to achieve both strategic depth and player engagement. To this end, we present a card-building tactical arena game built upon a multi-agent system, where players define card effects via natural language and interact with large language model–powered NPCs through negotiation or combat. Our system pioneers the use of multi-agent generative AI for constructing complete game mechanics, enabling a controllable mapping from natural language to structured game logic while ensuring design consistency through a predefined mechanism library and numerical constraints. A user study with 13 participants demonstrates that the system delivers a strategically rich and engaging gameplay experience, while also highlighting key areas for improvement—particularly in predictability, transparency, and player agency.
📝 Abstract
With advancements in generative AI technology, an increasing number of researchers have begun exploring AI-native games in which gameplay rules are directly driven by generative AI. This paper presents "Pharos Night: Crown Pursuit," an AI-native deck-building and tactical arena game based on a multi-agent system. The game uses large language models to generate materials and cards, support NPC decision-making, and mediate natural-language interactions. During play, players collect materials, describe desired card effects in natural language, and choose whether to negotiate or fight with NPCs in the arena. To constrain model-generated outcomes, the system parses responses as structured JSON, constructs card effects from predefined mechanics, and maps qualitative effect levels to designer-specified numerical values. A small-scale playtest with 13 participants suggests that the system can provide strategically meaningful and engaging AI-driven gameplay, while also revealing challenges related to predictability, transparency, and player control. This work demonstrates the potential of multi-agent generative AI systems for creating more emergent digital game experiences.
Innovation
Methods, ideas, or system contributions that make the work stand out.
AI-native game
multi-agent system
generative AI
large language model
structured generation
🔎 Similar Papers
No similar papers found.
