Procedural Content Metageneration via Program Search and Continual Abstraction Discovery

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.

The Time Value of Evolution

In evolutionary search, a weak child can be a valuable ancestor that makes high-fitness regions reachable. Immediate-return control is blind to this delayed utility, penalizing mutations through their immediate offspring even when they open productive future lineages. We formalize this hidden dynamic as the time value of evolution within a finite-horizon Markov decision process. To exploit it, we introduce Lineage-Value Policy Gradients (LVPG), a long-horizon actor-critic framework for automated trading policy discovery. Our architecture decouples search control into specialized policy heads over a shared generative backbone: a bootstrapped critic head estimates the value of finite-horizon lineage potential from multi-step mutation trees, while an actor head dynamically modulates mutation intensity over the remaining search budget. We isolate the impact of long-horizon credit assignment against immediate-return optimization across 90 paired runs under matched operators, lineage supervision, folds, seeds, and budgets. Path-based credit assignment substantially accelerates finite-budget search, increasing validation best-so-far AUC by 0.394 Sharpe units. LVPG also produces fewer temporary regressions than immediate-return optimization and recovers from them more often. Finite-horizon lineage value yields more selective non-monotonic search and stronger policies within identical resource constraints.

ELMER: Evolutionary Language Model that Explores and Refines

Program evolution can measure whether a mutation helped, but it rarely controls how far the mutation moves in behavior space. Syntactic edit size is an unreliable proxy: a small code change can alter nearly every action, while a larger rewrite can preserve the same execution trace. We introduce an Evolutionary Language Model that searches over natural-language policy descriptions and compiles typed programs for execution. A fully fine-tuned Qwen3-8B model learns three task-conditioned operations: conditional semantic mutation, natural language to domain-specific language (GPTL) compilation, and GPTL to natural language translation. The model is fine-tuned with conditional input on the mutation strength (low, medium, high) using Direct Preference Optimization (oDPO). Across 252 fixed-budget evolutionary searches, oDPO improves both behavioral calibration and finite-budget search efficiency. Natural-language attains the highest observed held-out fitness. Our analysis shows that the condition input (mutation strength) systematically changes semantic edit composition and that language mutations preserve more parent fitness at matched small-to-moderate behavioral displacement. These results show that language can serve as a steerable, execution-grounded search representation over executable program space.

Evolutionary Wave Function Collapse

Wave Function Collapse (WFC) is a widely used procedural content generation method that learns local adjacency constraints from example inputs to generate larger outputs. In this paper, we explore combining WFC with evolutionary search by evolving the small input examples used by WFC rather than directly evolving complete levels. In this approach, WFC acts as a genotype-to-phenotype mapping. The generated levels are then evaluated through domain-specific fitness functions. We evaluate the method in two domains with different relationships between local and global structure: Maze connectivity maps and Zelda-style dungeon layouts. Our results show that evolutionary optimization over WFC inputs improves generation quality in domains where properties emerge from local relationships, while domains requiring global constraints remain challenging. These findings suggest that evolutionary search can effectively guide WFC generation when target objectives align with local structure.

Learning Local Constraints for Reinforcement-Learned Content Generators

Constraint-based game content generators that learn local constraints from existing content, such as Wave Function Collapse (WFC), can generate visually satisfying game levels but face challenges in guaranteeing global properties, such as playability. On the other hand, reinforcement-learning trained generators can guarantee global properties -- because such properties can easily be included in reward functions -- but the results can be visually dissatisfying. In this paper, we explore ways to combine these methods. Specifically, we constrain the action space of a PCGRL generator with constraints learned by WFC, effectively allowing the PCGRL generator to achieve global properties while forced to adhere to local constraints. To better analyze how this hybrid content generation method operates, we vary the number and type of inputs, and we test whether to randomly collapse the starting state and exclude rare patterns. While the method is sensitive to hyperparameter tuning, the best of our trained generators produce visually satisfying and playable puzzle-platform game levels -- such as Lode Runner levels -- with desired global properties.

Continuous Program Search

Genetic Programming yields interpretable programs, but small syntactic mutations can induce large, unpredictable behavioral shifts, degrading locality and sample efficiency. We frame this as an operator-design problem: learn a continuous program space where latent distance has behavioral meaning, then design mutation operators that exploit this structure without changing the evolutionary optimizer. We make locality measurable by tracking action-level divergence under controlled latent perturbations, identifying an empirical trust region for behavior-local continuous variation. Using a compact trading-strategy DSL with four semantic components (long/short entry and exit), we learn a matching block-factorized embedding and compare isotropic Gaussian mutation over the full latent space to geometry-compiled mutation that restricts updates to semantically paired entry--exit subspaces and proposes directions using a learned flow-based model trained on logged mutation outcomes. Under identical $(μ+λ)$ evolution strategies and fixed evaluation budgets across five assets, the learned mutation operator discovers strong strategies using an order of magnitude fewer evaluations and achieves the highest median out-of-sample Sharpe ratio. Although isotropic mutation occasionally attains higher peak performance, geometry-compiled mutation yields faster, more reliable progress, demonstrating that semantically aligned mutation can substantially improve search efficiency without modifying the underlying evolutionary algorithm.

Evolutionary Level Repair

We address the problem of game level repair, which consists of taking a designed but non-functional game level and making it functional. This might consist of ensuring the completeness of the level, reachability of objects, or other performance characteristics. The repair problem may also be constrained in that it can only make a small number of changes to the level. We investigate search-based solutions to the level repair problem, particularly using evolutionary and quality-diversity algorithms, with good results. This level repair method is applied to levels generated using a machine learning-based procedural content generation (PCGML) method that generates stylistically appropriate but frequently broken levels. This combination of PCGML for generation and search-based methods for repair shows great promise as a hybrid procedural content generation (PCG) method.

ScriptDoctor: Automatic Generation of PuzzleScript Games via Large Language Models and Tree Search

There is much interest in using large pre-trained models in Automatic Game Design (AGD), whether via the generation of code, assets, or more abstract conceptualization of design ideas. But so far this interest largely stems from the ad hoc use of such generative models under persistent human supervision. Much work remains to show how these tools can be integrated into longer-time-horizon AGD pipelines, in which systems interface with game engines to test generated content autonomously. To this end, we introduce ScriptDoctor, a Large Language Model (LLM)-driven system for automatically generating and testing games in PuzzleScript, an expressive but highly constrained description language for turn-based puzzle games over 2D gridworlds. ScriptDoctor generates and tests game design ideas in an iterative loop, where human-authored examples are used to ground the system's output, compilation errors from the PuzzleScript engine are used to elicit functional code, and search-based agents play-test generated games. ScriptDoctor serves as a concrete example of the potential of automated, open-ended LLM-based workflows in generating novel game content.

The Procedural Content Generation Benchmark: An Open-source Testbed for Generative Challenges in Games

This paper introduces the Procedural Content Generation Benchmark for evaluating generative algorithms on different game content creation tasks. The benchmark comes with 12 game-related problems with multiple variants on each problem. Problems vary from creating levels of different kinds to creating rule sets for simple arcade games. Each problem has its own content representation, control parameters, and evaluation metrics for quality, diversity, and controllability. This benchmark is intended as a first step towards a standardized way of comparing generative algorithms. We use the benchmark to score three baseline algorithms: a random generator, an evolution strategy, and a genetic algorithm. Results show that some problems are easier to solve than others, as well as the impact the chosen objective has on quality, diversity, and controllability of the generated artifacts.

Affectively Framework: Towards Human-like Affect-Based Agents

Game environments offer a unique opportunity for training virtual agents due to their interactive nature, which provides diverse play traces and affect labels. Despite their potential, no reinforcement learning framework incorporates human affect models as part of their observation space or reward mechanism. To address this, we present the \emph{Affectively Framework}, a set of Open-AI Gym environments that integrate affect as part of the observation space. This paper introduces the framework and its three game environments and provides baseline experiments to validate its effectiveness and potential.