arXiv:2607. 02082v1 Announce Type: cross Abstract: Wave Function Collapse (WFC) is a widely used procedural content generation method that learns local adjacency constraints from example inputs to generate larger outputs.
arXiv:2605.13570v2 Announce Type: replace Abstract: Constraint-based game content generators that learn local constraints from existing content, such as Wave Function Collapse (WFC), can generate vis...
arXiv:2607. 11913v1 Announce Type: cross Abstract: Recent advancements in agentic AI have increasingly moved toward graph-based methods, driven by the demand for explainable, human-centered, and non-linear reasoning workflows.
arXiv:2603. 11863v2 Announce Type: replace Abstract: The saturation of high-quality pre-training data has shifted research focus toward evolutionary systems capable of continuously generating novel artifacts, leading to the success of AlphaEvolve.
EvoTreeNAD is a genealogy‑guided evolutionary algorithm that autonomously discovers neural architectures without a predefined seed or search space. Starting from an empty root, it builds a persistent genealogy where each node represents a complete architecture; top‑percentile values from nodes and descendants steer lineage selection. The method combines an Idea Agent that proposes variants and a Code Agent that implements them, with theoretical analysis showing stationary variation regimes and empirical results demonstrating superior performance on CIFAR‑10/100 and MedMNIST‑v2 tasks.
The paper introduces LLM-EBG, an evolutionary framework that uses a large language model as a generative operator to automatically create optimization benchmarks. By generating unconstrained single-objective continuous minimization problems expressed as mathematical formulas, the framework can produce benchmarks that consistently favor a target algorithm over a comparison algorithm in over 80% of trials. Landscape analysis shows that these generated problems exhibit distinct geometric traits, such as sensitivity to variable scaling, reflecting the search behaviors of different optimization methods.
The paper demonstrates that large language models can generate executable procedural content generators, enabling direct search over generator programs rather than individual levels. Using Sokoban, Zelda, Dangerous Dave, and Lode Runner, the authors evolve complete Python generators via language‑model mutation and crossover, and introduce Continual Abstraction Discovery (CAD) to extract reusable primitives into a run‑specific helper module. Experiments show that CAD consistently improves mean final best fitness across all domain and API comparisons, with learned libraries being adopted by subsequent programs and repeatedly rediscovering useful utilities.
arXiv:2607. 12097v1 Announce Type: new Abstract: Video games are a dynamic medium experienced over time.
arXiv:2407. 09013v2 Announce Type: replace Abstract: The attempt to utilize machine learning in PCG has been made in the past.
The paper investigates whether artificial evolution can replicate biological neuromodulation and diverse neuron types in indirectly encoded substrates. Experiments show that neuromodulation alone cannot overcome a 75% performance ceiling on parity tasks, but combining neuromodulation with per‑task activation function selection allows a single evolving genotype to achieve 100% success across five tasks. This demonstrates that both neuromodulation and evolvable computational primitives are necessary for multi‑behavioral open‑ended evolution.
The paper introduces ViralRecipesTrans, a dataset of execution flow graphs from culinary videos linked to specific creators, and proposes a graph learning framework to discover procedural personas. It shows that discrete topological metrics better capture a creator’s workflow than lexical classifiers, and presents a two‑stage generative model that predicts a creator’s exact execution graph for new dishes. The study finds that few‑shot LLMs excel at semantic assignment but lack macro‑planning, while the structured model offers superior topological control, and an ensemble approach combines both strengths for personalized workflow generation.
arXiv:2607. 10127v1 Announce Type: cross Abstract: Evolutionary program search guided by Large Language Models (LLMs) has emerged as a powerful paradigm for automated scientific discovery.
arXiv:2606. 02438v1 Announce Type: new Abstract: Learned heuristics have recently become a competitive alternative to traditional domain-independent heuristics for satisficing planning.