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

2025-05-21

AI Summary

Traditional pattern-centric approaches fail to uncover system-level ecological dynamics in Flow-Lenia—a continuous cellular automaton satisfying mass conservation and parameter localization. Method: We propose the first IMGEPs (Intrinsically Motivated Goal Exploration Processes) framework optimized for global behavioral metrics—including evolutionary activity, multiscale entropy, and compression-based complexity—and integrate it into a human-AI collaborative scientific discovery workflow featuring continuous modeling, multiscale analysis, and interactive visualization. Contribution/Results: Compared to random search, our method significantly improves the efficiency of discovering dynamic diversity. Empirical evaluation reveals emergent collective self-organization phenomena—such as stable coexistence, competitive exclusion, and hierarchical evolution—that remain undetected by individual-pattern methods. This work establishes a novel paradigm for investigating ecosystem-level self-organization in artificial life systems.

Technology Category

• Search and Optimization: Evolutionary Computation
• Machine Learning: Evolutionary Learning
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Web Mining and Content Analysis: Models for Web evolution
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

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.

Problem

• Discovering diverse ecosystem dynamics in Flow-Lenia
• Extending individual pattern search to interacting patterns
• Exploring emergent collective properties in complex systems

Innovation

• Curiosity-driven AI explores Flow-Lenia dynamics
• Diversity search with simulation-wide metrics
• Interactive tool enables human-AI collaboration