MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences
Zizhen Li, Chuanhao Li, Yibin Wang, Yukang Feng, Jianwen Sun, Jiaxin Ai, Fanrui Zhang, Mingzhu Sun, Yifei Huang, Kaipeng Zhang
2026-01-26
Summary
This paper explores how to make AI better at helping people design board games, going beyond just playing the game to actually giving useful feedback during the design process.
What's the problem?
Currently, AI can play board games, but it struggles to offer constructive criticism about a game's design because it doesn't understand how the rules create the actual experience for players. It's hard for AI to figure out how rules translate into fun (or not fun!) gameplay without actually *playing* the game through a computer simulation, and it's also difficult to account for the fact that different people enjoy different things in games.
What's the solution?
The researchers created a large collection of board game rulebooks and player reviews, and then they used a special framework called 'Mechanics-Dynamics-Aesthetics' to connect the rules of a game to what players actually experience. They then built a new AI model, called MeepleLM, that learns to think like different types of board game players and give feedback based on those perspectives. This model is specifically designed to understand and simulate how various players will react to a game's rules.
Why it matters?
This work is important because it moves us closer to AI that can truly collaborate with humans in creative tasks, like game design. MeepleLM can act as a 'virtual playtester,' providing valuable insights to designers and helping them create games that are more enjoyable and tailored to their target audience. It's a step towards AI that understands *why* people like or dislike things, not just *that* they do.
Abstract
Recent advancements have expanded the role of Large Language Models in board games from playing agents to creative co-designers. However, a critical gap remains: current systems lack the capacity to offer constructive critique grounded in the emergent user experience. Bridging this gap is fundamental for harmonizing Human-AI collaboration, as it empowers designers to refine their creations via external perspectives while steering models away from biased or unpredictable outcomes. Automating critique for board games presents two challenges: inferring the latent dynamics connecting rules to gameplay without an explicit engine, and modeling the subjective heterogeneity of diverse player groups. To address these, we curate a dataset of 1,727 structurally corrected rulebooks and 150K reviews selected via quality scoring and facet-aware sampling. We augment this data with Mechanics-Dynamics-Aesthetics (MDA) reasoning to explicitly bridge the causal gap between written rules and player experience. We further distill player personas and introduce MeepleLM, a specialized model that internalizes persona-specific reasoning patterns to accurately simulate the subjective feedback of diverse player archetypes. Experiments demonstrate that MeepleLM significantly outperforms latest commercial models (e.g., GPT-5.1, Gemini3-Pro) in community alignment and critique quality, achieving a 70% preference rate in user studies assessing utility. MeepleLM serves as a reliable virtual playtester for general interactive systems, marking a pivotal step towards audience-aligned, experience-aware Human-AI collaboration.