MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences

TL;DR

This work introduces MeepleLM, a specialized model that acts as a virtual playtester by translating static board game rulebooks into emergent gameplay experiences through an explicit MDA (Mechanics-Dynamics-Aesthetics) reasoning chain. It builds a large, high-quality dataset of 1,727 rulebooks and 150K critiques, augmented with data-driven player personas to generate persona-aligned feedback. Through a persona-conditioned instruction-tuning regime and a verifier-guided data filtration loop, MeepleLM achieves superior community alignment, factual fidelity, and practical utility compared with leading LLM baselines. The results demonstrate the model’s potential to accelerate design iteration and support audience-aligned Human-AI collaboration in interactive systems, while outlining future directions in multimodal understanding and finer-grained persona modeling.

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.

Figures (28)

• Figure 1: Overview of MeepleLM. Acting as a Virtual Playtester, the model offers a rapid, automated alternative to the resource-intensive Human Play loop. By leveraging MDA-Reasoning to infer latent dynamics from Static Rulebooks, MeepleLM generates Persona-Aligned Critiques tailored to diverse player archetypes.
• Figure 2: The Data Construction Pipeline. We structure 1,727 board game rulebooks and filter 1.8M reviews via multi-dimensional quality assessment, yielding 150K high-quality critiques for persona discovery.
• Figure 3: Impact of the Filtering Strategy. Our strategy enhances MDA scores and semantic coverage while preserving the original rating distribution.
• Figure 4: Tier-wise Prediction Alignment. MeepleLM shows a sharp diagonal concentration, effectively distinguishing quality tiers.
• Figure 5: Rating Density Distributions. MeepleLM demonstrates superior distributional fidelity by accurately recovering the high variance of human consensus.