Hybrid Voting-Based Task Assignment in Role-Playing Games

TL;DR

The paper tackles the problem of maintaining immersion in RPGs through long-form narratives by addressing the limitations of existing procedural content generation methods in multi-agent, context-rich environments. It introduces VBTA, a hybrid framework that combines structured Task Descriptions and Capability Profiles with semantic reasoning from LLMs, a suitability matrix, six voting methods, and three allocation strategies, augmented by conflict-based search for path planning. A key contribution is the integration of LLM-based ambiguity resolution and CBS-driven planning to enable dynamic, coherent assignment and action planning across narrative, dialogue, and combat scenarios. The use cases in Dungeons & Dragons and Baldur's Gate 3 demonstrate VBTA’s potential to generate diverse, evolving content and adapt to player actions, offering a path toward scalable, immersive, procedurally generated RPG experiences. The approach has broad implications for game AI and human-robot interaction, suggesting that combining formal task allocation with semantic interpretation and planning can enhance realism, replayability, and developer productivity in complex multi-agent systems.

Abstract

In role-playing games (RPGs), the level of immersion is critical-especially when an in-game agent conveys tasks, hints, or ideas to the player. For an agent to accurately interpret the player's emotional state and contextual nuances, a foundational level of understanding is required, which can be achieved using a Large Language Model (LLM). Maintaining the LLM's focus across multiple context changes, however, necessitates a more robust approach, such as integrating the LLM with a dedicated task allocation model to guide its performance throughout gameplay. In response to this need, we introduce Voting-Based Task Assignment (VBTA), a framework inspired by human reasoning in task allocation and completion. VBTA assigns capability profiles to agents and task descriptions to tasks, then generates a suitability matrix that quantifies the alignment between an agent's abilities and a task's requirements. Leveraging six distinct voting methods, a pre-trained LLM, and integrating conflict-based search (CBS) for path planning, VBTA efficiently identifies and assigns the most suitable agent to each task. While existing approaches focus on generating individual aspects of gameplay, such as single quests, or combat encounters, our method shows promise when generating both unique combat encounters and narratives because of its generalizable nature.