Landmarks, Monuments, and Beacons: Understanding Generative Calls to Action

2025-09-23

AI Summary

Procedural content generation (PCG) lacks evaluation metrics aligned with human experience—particularly for composite game content. Method: We propose a player-perception–driven, three-level decomposition framework—Landmarks, Monuments, and Beacons—that formally models perceptibility, affective resonance, and action affordance, respectively. This is the first work to formalize humanities-informed perspectives from game studies as a computable, nested structural model. Our approach integrates game AI techniques with humanities-inspired analysis, leveraging existing content recognition methods to automatically decompose generated content and evaluate each component across multiple dimensions. Contribution/Results: The framework supports hybrid generation across diverse game genres and establishes a generalized, automated evaluation pipeline. It significantly improves measurability and controllability of generated content with respect to semantic coherence and experiential quality.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

Algorithmic evaluation of procedurally generated content struggles to find metrics that align with human experience, particularly for composite artefacts. Automatic decomposition as a possible solution requires concepts that meet a range of properties. To this end, drawing on Games Studies and Game AI research, we introduce the nested concepts of extit{Landmarks}, extit{Monuments}, and extit{Beacons}. These concepts are based on the artefact's perceivability, evocativeness, and Call to Action, all from a player-centric perspective. These terms are generic to games and usable across genres. We argue that these entities can be found and evaluated with techniques currently used in both research and industry, opening a path towards a fully automated decomposition of PCG, and evaluation of the salient sub-components. Although the work presented here emphasises mixed-initiative PCG and compositional PCG, we believe it applies beyond those domains. With this approach, we intend to create a connection between humanities and technical game research and allow for better computational PCG evaluation

Problem

• Finding metrics aligning algorithmic evaluation with human experience for generated content
• Developing concepts for automatic decomposition of procedurally generated composite artefacts
• Creating player-centric evaluation methods for perceivability and evocativeness in games

Innovation

• Introduces nested Landmarks Monuments Beacons concepts
• Uses perceivability evocativeness Call to Action metrics
• Applies automated decomposition techniques for PCG evaluation