MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences

TL;DR

MeepleLM is a specialized language model designed to simulate diverse player experiences and provide constructive critique for board game design, enhancing human-AI collaboration.

Contribution

The paper introduces MeepleLM, a novel model that internalizes player personas and bridges rules to player experience, outperforming commercial models in critique quality.

Findings

MeepleLM outperforms GPT-5.1 and Gemini3-Pro in user preference tests.

The dataset includes 1,727 rulebooks and 150K reviews with MDA reasoning.

MeepleLM achieves a 70% preference rate in community alignment and critique utility.

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.