AutoBG: A Board Game Design Assistant with Interactive Ideation, Iterative Rulebook Generation, and Individualized Feedback

2026-06-01

AI Summary

This work addresses the complexity of tabletop game design—a multifaceted process spanning ideation, rule authoring, and playtesting—by introducing the first human-centered collaborative framework that offers end-to-end support. The proposed system integrates four core modules (BG-Ideator, BG-Realizer, BG-Critic, and BG-Persona) to facilitate interactive ideation, critique-driven iterative refinement of rulebooks, and personalized feedback grounded in authentic player personas. Trained on 2.2K structured rulebooks and 180K curated player reviews, the framework significantly outperforms strong baselines such as GPT-5.4 across 207 unseen games, producing rulebooks approaching publication quality. A user study with 30 participants demonstrates its effectiveness in alleviating design anxiety, uncovering latent flaws, and delivering highly actionable support throughout the creative workflow.

Abstract

Designing a board game demands both thinking as a designer and experiencing as a player, while iterating through repeated prototyping and playtesting cycles, making it a cognitively intensive creative task well suited for human-AI collaboration. However, current systems lack end-to-end support to guide designers through the complete workflow from vague early ideation to iterative rulebook revision and audience testing. To this end, we present AutoBG, a board game design assistant built around critic-driven iterative refinement, comprising four specialized modules: BG-Ideator guides designers via multi-turn dialogue to produce structured design drafts; BG-Realizer generates complete rulebooks from drafts and revises them in a closed loop with BG-Critic, which diagnoses design flaws and gates each revision so that only verified improvements are accepted; and BG-Persona simulates individualized feedback from 150 real player profiles. Together, these modules enable designers to go from an initial idea to a polished, audience-tested rulebook within a single integrated workflow. The system is built on 2.2K structured rulebooks and 180K quality-filtered real player reviews, with task-specific training data derived for each module. Experiments on 207 held-out games show that AutoBG substantially outperforms state-of-the-art baselines (e.g., GPT-5.4), generating rulebooks that approach the quality of published games. Furthermore, a user study with 30 participants across diverse experience levels confirms that AutoBG effectively reduces blank-page anxiety, surfaces hidden design flaws, and provides highly rated, practical assistance throughout the creative process.

Problem

• board game design
• end-to-end support
• iterative rulebook generation
• audience testing
• design workflow

Innovation

• interactive ideation
• iterative rulebook generation
• critic-driven refinement
• personalized player feedback
• human-AI co-creation