Related papers: Flow-Lenia: Towards open-ended evolution in cellul…
We introduce Neural Particle Automata (NPA), a Lagrangian generalization of Neural Cellular Automata (NCA) from static lattices to dynamic particle systems. Unlike classical Eulerian NCA where cells are pinned to pixels or voxels, NPA model…
Large Language Models (LLMs) have advanced rapidly in recent years, demonstrating strong capabilities in problem comprehension and reasoning. Inspired by these developments, researchers have begun exploring the use of LLMs as decentralized…
Guiding biological systems toward desired states, such as morphogenetic outcomes, remains a fundamental challenge with far-reaching implications for medicine and synthetic biology. While large language models (LLMs) have enabled natural…
This paper describes a new concept of cellular automaton (CA). XCA consists of a set of arcs (edges) that correspond to cells in CA. At a particular time, the arcs are connected to a directed graph. With each time step, the arcs exchange…
A firm cognitive subject or ``individual'' is presupposed for the emergence of mind. However, with the development of recent information technology, the ``individual'' has become more dispersed in society and the cognitive subject has…
In this work, a conceptual bio-inspired parallel and distributed learning framework for the emergence of general intelligence is proposed, where agents evolve through environmental rewards and learn throughout their lifetime without…
The Gaia hypothesis considers the life-environment coupled system as a single entity that acts to regulate and maintain habitable conditions on Earth. In this paper we discuss three mechanisms which could potentially lead to Gaia: Selection…
We created two dimensional hexagonal cellular automata to obtain complexity. Considering the game of life rules, Wolfram's works about life-like structures and John von Neumann's self-replication, self-maintenance, self-reproduction…
Cellular automata generate spatially extended, temporally persistent emergent structures from local update rules. No general method derives the mechanisms of that generation from the rule itself; existing tools reconstruct structure from…
Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and maintain persistent memory. However, we show that such self-evolution is often…
Conway's Game of Life (Life), a well known algorithm within the broader class of cellular automata (CA), exhibits complex emergent dynamics, with extreme sensitivity to initial conditions. Modeling and predicting such intricate behavior…
As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Scaling training-time…
A multispecies artificial ecosystem is formulated using cellular automata with species interactions and food chain hierarchy. The constructed finite state automaton can simulate the complexity and self-organized characteristics of the…
Establishing the emergence of evolutionary behavior as a defining characteristic of 'life' is a major step in the Artificial life (ALife) studies. We present here an abstract formal framework for this aim based upon the notion of high-level…
We propose a four-way classification of two-dimensional semi-totalistic cellular automata that is different than Wolfram's, based on two questions with yes-or-no answers: do there exist patterns that eventually escape any finite bounding…
Artificial and biological systems may evolve similar computational solutions despite fundamental differences in architecture and learning mechanisms -- a form of convergent evolution. We demonstrate this phenomenon through large-scale…
We study open-ended evolution by focusing on computational and information-processing dynamics underlying major evolutionary transitions. In doing so, we consider biological organisms as hierarchical dynamical systems that generate…
Robotic Process Automation (RPA) systems face challenges in handling complex processes and diverse screen layouts that require advanced human-like decision-making capabilities. These systems typically rely on pixel-level encoding through…
Learning long-horizon robotic manipulation requires jointly achieving expressive behavior modeling, real-time inference, and stable execution, which remains challenging for existing generative policies. Diffusion-based approaches offer…
This paper presents LLM2TEA, a Large Language Model (LLM) driven MultiTask Evolutionary Algorithm, representing the first agentic AI designer of its kind operating with generative evolutionary multitasking (GEM). LLM2TEA enables the…