arXiv AI
Programmable Cellular Automata
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
3d ago
Why Do Conventional World Models Fail to Learn Cellular Automata?
arXiv:2609.39604v1 Announce Type: new Abstract: Although conventional world models - auto-regressive or diffusion models based on transformers or convolutional networks - may learn surface statistics...
arXiv Machine Learning
Aug 17
It's Much Easier for Neural Networks to learn Game of Life Dynamics with the Right Activation Function: Polynomial Kolmogorov-Arnold Networks
arXiv:2606. 23587v2 Announce Type: replace Abstract: Previous work has found a gap between the scale of neural networks that reliably learn Conway's Game of Life, and minimal networks capable of representing the classic cellular automaton with hard-coded parameter values.
arXiv Machine Learning
Aug 17
Emergent Models: Intelligence from Tiny Substrates
arXiv:2608. 14019v1 Announce Type: cross Abstract: Emergent Models (EMs) are a machine learning paradigm based on simple yet open-ended substrates, such as cellular automata, in which modeling is treated not as the learning of a closed-form input-output map but as the emergence, within simple dynamical systems, of computational behaviors that solve external tasks.
arXiv AI
Jul 10
Architecture Generalization with MetaNCA
arXiv:2607. 07743v1 Announce Type: cross Abstract: Self-organization is an emergent property of life, driven by the collective behavior of individual components acting on local information.
arXiv AI
Sep 17
Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization
The paper introduces Gauntlet, a framework that lets large language models autonomously build game-playing agents from a bare contract—just a game description, raw observation/action interface, and an empty policy file. In a single session, the model experiments with the game, compiles a standalone controller, and the resulting program is evaluated on held‑out instances without further model calls. The authors demonstrate that these compiled agents can win full‑scale games such as StarCraft II and Civilization, marking the first time a language‑agent system has achieved standalone victory in such complex titles.
arXiv AI
Aug 6
Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language
arXiv:2608. 04384v1 Announce Type: new Abstract: Neural PDE solver auto-design is fundamentally a search-space representation problem.