# Procedural Content Metageneration via Program Search and Continual Abstraction Discovery

arXiv: https://arxiv.org/abs/2608.17947 · HTML: https://mlsanity.com/paper/2608.17947/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Procedural Content Generation via Machine Learning (PCGML)](https://mlsanity.com/paper/1702.00539/) (2017)
- [Large Language Models and Games: A Survey and Roadmap](https://mlsanity.com/paper/2402.18659/) (2024)
- [PCGRL: Procedural Content Generation via Reinforcement Learning](https://mlsanity.com/paper/2001.09212/) (2020)
- [Deep Learning for Procedural Content Generation](https://mlsanity.com/paper/2010.04548/) (2020)
- [Level Generation Through Large Language Models](https://mlsanity.com/paper/2302.05817/) (2023)
- [MarioGPT: Open-Ended Text2Level Generation through Large Language Models](https://mlsanity.com/paper/2302.05981/) (2023)
- [An AI system to help scientists write expert-level empirical software](https://mlsanity.com/paper/2509.06503/) (2025)
- [Game Generation via Large Language Models](https://mlsanity.com/paper/2404.08706/) (2024)
- [Large Language Models and Video Games: A Preliminary Scoping Review](https://mlsanity.com/paper/2403.02613/) (2024)
- [Practical PCG Through Large Language Models](https://mlsanity.com/paper/2305.18243/) (2023)
- [Word2World: Generating Stories and Worlds through Large Language Models](https://mlsanity.com/paper/2405.06686/) (2024)
- [Multi-Objective level generator generation with Marahel](https://mlsanity.com/paper/2005.08368/) (2020)
- [The Procedural Content Generation Benchmark: An Open-source Testbed for Generative Challenges in Games](https://mlsanity.com/paper/2503.21474/) (2025)

## Abstract (arXiv)

Large language models can generate executable programs, which makes it possible to search directly over procedural content generators rather than individual levels. We study this approach in Sokoban, Zelda, Dangerous Dave, and Lode Runner. Each run evolves complete Python generators through language-model mutation and crossover. We introduce Continual Abstraction Discovery, or CAD, which extracts reusable primitives from high-fitness programs into a run-specific helper module. A 2x2 experiment crosses CAD with access to a fixed hand-written domain API. The completed data set contains 160 complete runs, with at least ten 50-generation runs in every cell. CAD raises mean final best fitness in all eight domain and API comparisons. Across all CAD runs, learned libraries are adopted by most later programs and repeatedly rediscover validation, reachability, and structural utilities. These results support that discovering reusable primitives improves evolutionary program search for content generators.