Expedition & Expansion: Leveraging Semantic Representations for Goal-Directed Exploration in Continuous Cellular Automata

2025-09-03

AI Summary

High-dimensional behavioral spaces in continuous cellular automata (CA) hinder systematic exploration of diverse visual patterns, causing conventional novelty search to stagnate locally. To address this, we propose a semantics-guided collaborative exploration framework for Flow Lenia: it integrates novelty search with vision-language models (VLMs) to generate human-interpretable semantic descriptions of emergent patterns—serving as long-range exploration targets—while incorporating genealogical lineage analysis to ensure diversity and coherence of evolutionary trajectories. This approach overcomes local optimization traps by actively steering cross-regional behavioral discovery within a structured semantic space. Experiments demonstrate that our method significantly enhances the richness and diversity of dynamic patterns compared to baseline approaches; moreover, “expeditionary” solutions—those achieving distant semantic targets—dominate long-term exploration paths. To our knowledge, this is the first work enabling targeted CA behavioral evolution guided by human-understandable semantic objectives.

Technology Category

• Search and Optimization: Evolutionary Computation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Models for Web evolution
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Discovering diverse visual patterns in continuous cellular automata (CA) is challenging due to the vastness and redundancy of high-dimensional behavioral spaces. Traditional exploration methods like Novelty Search (NS) expand locally by mutating known novel solutions but often plateau when local novelty is exhausted, failing to reach distant, unexplored regions. We introduce Expedition and Expansion (E&E), a hybrid strategy where exploration alternates between local novelty-driven expansions and goal-directed expeditions. During expeditions, E&E leverages a Vision-Language Model (VLM) to generate linguistic goals--descriptions of interesting but hypothetical patterns that drive exploration toward uncharted regions. By operating in semantic spaces that align with human perception, E&E both evaluates novelty and generates goals in conceptually meaningful ways, enhancing the interpretability and relevance of discovered behaviors. Tested on Flow Lenia, a continuous CA known for its rich, emergent behaviors, E&E consistently uncovers more diverse solutions than existing exploration methods. A genealogical analysis further reveals that solutions originating from expeditions disproportionately influence long-term exploration, unlocking new behavioral niches that serve as stepping stones for subsequent search. These findings highlight E&E's capacity to break through local novelty boundaries and explore behavioral landscapes in human-aligned, interpretable ways, offering a promising template for open-ended exploration in artificial life and beyond.

Problem

• Overcoming exploration plateaus in continuous cellular automata
• Generating semantic goals for distant unexplored regions
• Enhancing interpretability of discovered behavioral patterns

Innovation

• Uses Vision-Language Model for goal generation
• Combines local novelty with semantic expeditions
• Operates in human-aligned semantic spaces