mlsanityData to 14 Oct 2026

Mortar: Evolving Mechanics for Automatic Game Design

arXiv 2601.00105 ↗First posted 31 Dec 2025cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We present Mortar, a system for autonomously evolving game mechanics for automatic game design. Game mechanics define the rules and interactions that govern gameplay, and designing them manually is a time-consuming and expert-driven process. Mortar combines a quality-diversity algorithm with a large language model to explore a diverse set of mechanics, which are evaluated by synthesising complete games that incorporate both evolved mechanics and those drawn from an archive. The mechanics are evaluated by composing complete games through a tree search procedure, where the resulting games are evaluated by their ability to preserve a skill-based ordering over players -- that is, whether stronger players consistently outperform weaker ones. We assess the mechanics based on their contribution towards the skill-based ordering score in the game. We demonstrate that Mortar produces games that appear diverse and playable, and mechanics that contribute more towards the skill-based ordering score in the game. We perform ablation studies to assess the role of each system component and a user study to evaluate the games based on human feedback.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 42 references that are in the map. First posted on arXiv 31 Dec 2025.

Builds on

21 of 42 references.

References · 21

  1. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  2. 2015Illuminating search spaces by mapping elitescited by 425
  3. 2024Reinforcement learningcited by 247
  4. 2022Evolution through Large Modelscited by 134
  5. 2023LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimizationcited by 87
  6. 2020Deep Learning for Procedural Content Generationcited by 73
  7. 2023Level Generation Through Large Language Modelscited by 68
  8. 2023MarioGPT: Open-Ended Text2Level Generation through Large Language Modelscited by 64
  9. 2019Increasing Generality in Machine Learning through Procedural Content Generationcited by 59
  10. 2024GAVEL: Generating Games Via Evolution and Language Modelscited by 24
  11. 2023Practical PCG Through Large Language Modelscited by 21
  12. 2024Word2World: Generating Stories and Worlds through Large Language Modelscited by 18
9 more
  1. 2019General Video Game Rule Generationcited by 17
  2. 2018A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarkingcited by 6
  3. 2019Automatic Game Design via Mechanic Generationcited by 5
  4. 2023Mechanic Maker 2.0: Reinforcement Learning for Evaluating Generated Rulescited by 4
  5. 2024Mechanic Maker: Accessible Game Development Via Symbolic Learning Program Synthesiscited by 3
  6. 2025Word2Minecraft: Generating 3D Game Levels through Large Language Modelscited by 3
  7. 2017Evolving Game Skill-Depth using General Video Game AI Agentscited by 2
  8. 2025ScriptDoctor: Automatic Generation of PuzzleScript Games via Large Language Models and Tree Searchcited by 2
  9. 2019Automatic Critical Mechanic Discovery Using Playtraces in Video Gamescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Programmable Cellular Automatacited by 0