dorsal/arxiv
View SchemaMeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences
| Authors | Zizhen Li, Chuanhao Li, Yibin Wang, Yukang Feng, Jianwen Sun, Jiaxin Ai, Fanrui Zhang, Mingzhu Sun, Yifei Huang, Kaipeng Zhang |
|---|---|
| Categories | |
| ArXiv ID | 2601.07251vv1 |
| URL | https://arxiv.org/abs/2601.07251 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
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.
{
"annotation_id": "cb4995c2-e809-4a3a-910c-0102a806f871",
"date_created": "2026-02-17T05:53:12.009000Z",
"date_modified": "2026-02-17T05:53:12.009000Z",
"file_hash": "625b4e4984e3fa0c0c16e0d448637b648c96f972b901192696cad0b080461e01",
"private": false,
"record": {
"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.",
"arxiv_id": "2601.07251",
"authors": [
"Zizhen Li",
"Chuanhao Li",
"Yibin Wang",
"Yukang Feng",
"Jianwen Sun",
"Jiaxin Ai",
"Fanrui Zhang",
"Mingzhu Sun",
"Yifei Huang",
"Kaipeng Zhang"
],
"categories": [
"cs.HC"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences",
"url": "https://arxiv.org/abs/2601.07251",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "fbd953ec-4892-4488-b302-10a22300386d",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}