Exploring Flow-Lenia Universes with a Curiosity-driven AI Scientist: Discovering Diverse Ecosystem Dynamics

• URL: http://arxiv.org/abs/2505.15998v2
• Date: Mon, 02 Jun 2025 14:48:26 GMT
• Title: Exploring Flow-Lenia Universes with a Curiosity-driven AI Scientist: Discovering Diverse Ecosystem Dynamics
• Authors: Thomas Michel, Marko Cvjetko, Gautier Hamon, Pierre-Yves Oudeyer, Clément Moulin-Frier,
• Abstract summary: We present a method for the automated discovery of system-level dynamics in Flow-Lenia--a continuous cellular automaton (CA)<n>This method aims to uncover processes leading to self-organization of evolutionary and ecosystemic dynamics in CAs.
• Score: 17.425135648759515
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a method for the automated discovery of system-level dynamics in Flow-Lenia--a continuous cellular automaton (CA) with mass conservation and parameter localization-using a curiosity--driven AI scientist. This method aims to uncover processes leading to self-organization of evolutionary and ecosystemic dynamics in CAs. We build on previous work which uses diversity search algorithms in Lenia to find self-organized individual patterns, and extend it to large environments that support distinct interacting patterns. We adapt Intrinsically Motivated Goal Exploration Processes (IMGEPs) to drive exploration of diverse Flow-Lenia environments using simulation-wide metrics, such as evolutionary activity, compression-based complexity, and multi-scale entropy. We test our method in two experiments, showcasing its ability to illuminate significantly more diverse dynamics compared to random search. We show qualitative results illustrating how ecosystemic simulations enable self-organization of complex collective behaviors not captured by previous individual pattern search and analysis. We complement automated discovery with an interactive exploration tool, creating an effective human-AI collaborative workflow for scientific investigation. Though demonstrated specifically with Flow-Lenia, this methodology provides a framework potentially applicable to other parameterizable complex systems where understanding emergent collective properties is of interest.

Related papers

• A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence [87.08051686357206]
  Large Language Models (LLMs) have demonstrated strong capabilities but remain fundamentally static.<n>As LLMs are increasingly deployed in open-ended, interactive environments, this static nature has become a critical bottleneck.<n>This survey provides the first systematic and comprehensive review of self-evolving agents.
  arXiv  Detail & Related papers  (2025-07-28T17:59:05Z)
• Integrating Dynamical Systems Learning with Foundational Models: A Meta-Evolutionary AI Framework for Clinical Trials [0.0]
  NetraAI is a system-based framework engineered for stability and interpretability on small clinical trial datasets.<n>We formalize NetraAI's foundations, combining contraction mappings, information geometry, and evolutionary algorithms to identify predictive patient cohorts.<n>By prioritizing reliable, explainable knowledge, NetraAI offers a new generation of adaptive, self-reflective AI to accelerate clinical discovery.
  arXiv  Detail & Related papers  (2025-05-25T03:34:33Z)
• Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems [24.014942930679855]
  We introduce an encoder-only approach to learn the evolution operators of non-scale dynamical systems.<n>We show it across multiple scientific domains: explaining the folding dynamics of small proteins in host sites, and autonomously finding patterns in climate data.
  arXiv  Detail & Related papers  (2025-05-24T12:18:19Z)
• AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Research [58.944125758758936]
  The Science of Science (SoS) explores the mechanisms underlying scientific discovery.<n>The advent of artificial intelligence (AI) presents a transformative opportunity for the next generation of SoS.<n>We outline the advantages of AI over traditional methods, discuss potential limitations, and propose pathways to overcome them.
  arXiv  Detail & Related papers  (2025-05-17T15:01:33Z)
• Embodied World Models Emerge from Navigational Task in Open-Ended Environments [5.785697934050656]
  We ask whether a recurrent agent, trained solely by sparse rewards to solve procedurally generated planar mazes, can autonomously internalize metric concepts such as direction, distance and obstacle layout.<n>After training, the agent consistently produces near-optimal paths in unseen mazes, behavior that hints at an underlying spatial model.
  arXiv  Detail & Related papers  (2025-04-15T17:35:13Z)
• Learning System Dynamics without Forgetting [60.08612207170659]
  We investigate the problem of Continual Dynamics Learning (CDL), examining task configurations and evaluating the applicability of existing techniques.<n>We propose the Mode-switching Graph ODE (MS-GODE) model, which integrates the strengths LG-ODE and sub-network learning with a mode-switching module.<n>We construct a novel benchmark of biological dynamic systems for CDL, Bio-CDL, featuring diverse systems with disparate dynamics.
  arXiv  Detail & Related papers  (2024-06-30T14:55:18Z)
• Toward Artificial Open-Ended Evolution within Lenia using Quality-Diversity [5.380545611878407]
  We show that Quality-Diversity is an effective framework for the automatic discovery of diverse self-organizing patterns in complex systems. Our framework, called Leniabreeder, can leverage both manually defined diversity criteria and unsupervised measures of diversity to broaden the scope of discoverable patterns.
  arXiv  Detail & Related papers  (2024-06-06T16:35:27Z)
• Cognitive Evolutionary Learning to Select Feature Interactions for Recommender Systems [59.117526206317116]
  We show that CELL can adaptively evolve into different models for different tasks and data. Experiments on four real-world datasets demonstrate that CELL significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-05-29T02:35:23Z)
• Discovering Sensorimotor Agency in Cellular Automata using Diversity Search [17.898087201326483]
  In cellular automata (CA), a key open-question has been whether it is possible to find environment rules that self-organize. We show that this approach enables to find systematically environmental conditions in CA leading to self-organization. We show that the discovered agents have surprisingly robust capabilities to move, maintain their body integrity and navigate among various obstacles.
  arXiv  Detail & Related papers  (2024-02-14T14:30:42Z)
• Deep Learning-based Analysis of Basins of Attraction [49.812879456944984]
  This research addresses the challenge of characterizing the complexity and unpredictability of basins within various dynamical systems. The main focus is on demonstrating the efficiency of convolutional neural networks (CNNs) in this field.
  arXiv  Detail & Related papers  (2023-09-27T15:41:12Z)
• Incremental procedural and sensorimotor learning in cognitive humanoid robots [52.77024349608834]
  This work presents a cognitive agent that can learn procedures incrementally. We show the cognitive functions required in each substage and how adding new functions helps address tasks previously unsolved by the agent. Results show that this approach is capable of solving complex tasks incrementally.
  arXiv  Detail & Related papers  (2023-04-30T22:51:31Z)
• Action Matching: Learning Stochastic Dynamics from Samples [10.46643972142224]
  Action Matching is a method for learning a rich family of dynamics using only independent samples from its time evolution. We derive a tractable training objective, which does not rely on explicit assumptions about the underlying dynamics. Inspired by connections with optimal transport, we derive extensions of Action Matching to learn differential equations and dynamics involving creation and destruction of probability mass.
  arXiv  Detail & Related papers  (2022-10-13T01:49:48Z)
• Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning [12.76337275628074]
  In this work, we propose a variational dynamic model based on the conditional variational inference to model the multimodality andgenerativeity. We derive an upper bound of the negative log-likelihood of the environmental transition and use such an upper bound as the intrinsic reward for exploration. Our method outperforms several state-of-the-art environment model-based exploration approaches.
  arXiv  Detail & Related papers  (2020-10-17T09:54:51Z)
• Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems [21.23182328329019]
  We introduce a novel dynamic and modular architecture that enables unsupervised learning of a hierarchy of diverse representations. We show that this system forms a discovery assistant that can efficiently adapt its diversity search towards preferences of a user.
  arXiv  Detail & Related papers  (2020-07-02T15:28:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.