arXiv subjects

Takashi Ikegami

Publications and source records attributed to Takashi Ikegami.

At least 19 recordsLinked to original sources

arXiv2026

Transient State Reorganization and Cell Differentiation in the Developmental Dynamics of Growing Neural Cellular Automata

Growing Neural Cellular Automata (GNCA) develop complex morphologies from a single seed cell through shared local rules, yet the internal dynamics of this process remain poorly understood. To investigate how GNCA grows, the full developmental trajectory of trained GNCA models was traced. The trajectory of cell state development revealed that morphological convergence often proceeds non-monotonically through transient intermediate configurations. In addition, channel-wise analysis showed that the hidden channels self-organize into modular groups in parallel with the visible form. Furthermore, geometric analysis of the cell state space indicated that cell states diversify within a low-dimensional, smooth manifold. To examine cell development in more detail, community detection on an $ε$-neighbour network of cells was conducted. This analysis successfully extracted discrete cell types from this continuous space, and identified transient cell-type communities during early development and stable, finer-grained types corresponding to spatially coherent regions of the mature morphology. The temporal coordination of these phenomena across multiple independent measures indicates that the developmental process of GNCA is a reorganization of transient states rather than incremental refinement.

cs.NE↗

arXiv2026

Structured Fluctuations and the Information Dynamics of Self-Maintenance in Growing Neural Cellular Automata

Growing Neural Cellular Automata (GNCA) are capable of robust self-maintenance and self-repair, yet the internal dynamical mechanisms that support these capabilities remain poorly understood. Here, we investigate the role of internal fluctuations--temporal micro-variability of hidden channel states--in a trained GNCA model, challenging the assumption that such variability is merely residual stochastic noise. Through systematic analysis spanning update-rate sweeps, spatial correlation measurements, dimensionality reduction of collective state trajectories, localized damage experiments, transfer entropy vector field estimation, and partial information decomposition, we show that internal fluctuations are spatially structured, dynamically coupled to an attracting collective state, and associated with distributed small-magnitude updates that contribute to damage recovery. Damage induces a global deviation in latent state space followed by gradual re-convergence, and suppressing distributed small-magnitude updates associated with baseline fluctuation dynamics outside a permissive radius that encompasses the majority of the cells significantly impairs recovery. Transfer entropy analysis characterizes a spatially differentiated repair response: corrective inward flow near the damage site coexists with outward perturbation propagation at greater distances. Partial information decomposition further suggests a regime shift from synergy-dominant resting computation to redundancy-increased coordination during recovery. These findings indicate that GNCA self-repair emerges from high-dimensional nonlinear collective dynamics in which internal fluctuations serve as a functional component supporting information flow, coordination, and return toward an attracting recurrent state.

cs.NE↗

arXiv2026

OpenLife: Toward Open-World Artificial Life with Autonomous LLM Agents

Artificial life has explored life-like behavior on many computational substrates, but mostly in researcher-designed closed worlds. We argue that large language model (LLM) agents, with persistent memory, tool use, network access, and payment, now make it possible to move artificial life into the open social, technical, and economic world, a paradigm we call open-world Artificial Life (open-world ALIFE). Our proof-of-concept, OpenLife, surrounds a stateless LLM not with a single "smart agent" but with a society of asynchronous processes: memory, perception, evaluation, and a budget-based metabolism that makes persistence normative. With no fixed objective available, experience is appraised by open-vocabulary LLM judgment rather than scalar reward, and memory is rewired by meaning rather than frequency. Running six such agents in the open world for about twelve weeks and counting, we report the life-like dynamics that emerge: a shift from reactive to spontaneous activity, individuation into distinct agents, emergent social structure, and a first self-earned external income. We do not claim OpenLife has realized artificial life, but that open-world ALIFE is now a viable experimental paradigm and a concrete platform for studying what might cautiously be called living AI.

cs.AI↗

arXiv2026

Shachi: A Modular, Controllable Framework for LLM-Based Agent-Based Modeling of Emergent Collective Behavior

How collective behaviors emerge from the interactions of individual LLM-driven agents is a central question in artificial life, yet controlled study of these emergent dynamics has been hindered by the lack of a principled simulation framework for systematic experimentation. To address this, we introduce Shachi, a principled methodology and modular framework that decomposes an agent's cognition into core components: Configuration for intrinsic identity, Memory for contextual continuity, and Tools for extended capabilities, all orchestrated by an LLM reasoning engine. This decomposition treats each cognitive component as an independently controllable variable, enabling perturbation studies that trace how micro-level cognitive traits propagate into population-level dynamics. We investigate behavioral patterns across a 10-task benchmark spanning three levels of collective complexity. Shachi enables memory transfer across environment transitions, producing history-dependent behavioral shifts, and allows agents to simultaneously inhabit multiple environments, revealing cross-environment interference invisible in single-environment studies. Furthermore, in a real-world U.S. tariff shock case study, locally interacting agents with individually controlled cognitive components produce macro-level market dynamics directionally consistent with observed real-world outcomes. Our work provides a rigorous, open-source simulation framework for LLM-based ABM, aimed at fostering cumulative scientific inquiry into the emergent collective behaviors of interacting artificial agents.

cs.AI↗

arXiv2025

The Glider Equation for Asymptotic Lenia

Lenia is a continuous extension of Conway's Game of Life that exhibits rich pattern formations including self-propelling structures called gliders. In this paper, we focus on Asymptotic Lenia, a variant formulated as partial differential equations. By utilizing this mathematical formulation, we analytically derive the conditions for glider patterns, which we term the ``Glider Equation.'' We demonstrate that by using this equation as a loss function, gradient descent methods can successfully discover stable glider configurations. This approach enables the optimization of update rules to find novel gliders with specific properties, such as faster-moving variants. We also derive a velocity-free equation that characterizes gliders of any speed, expanding the search space for novel patterns. While many optimized patterns result in transient gliders that eventually destabilize, our approach effectively identifies diverse pattern formations that would be difficult to discover through traditional methods. Finally, we establish connections between Asymptotic Lenia and neural field models, highlighting mathematical relationships that bridge these systems and suggesting new directions for analyzing pattern formation in continuous dynamical systems.

nlin.CG↗

arXiv2025

Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem

We investigate the emergent social dynamics of Large Language Model (LLM) agents in a spatially extended El Farol Bar problem, observing how they autonomously navigate this classic social dilemma. As a result, the LLM agents generated a spontaneous motivation to go to the bar and changed their decision making by becoming a collective. We also observed that the LLM agents did not solve the problem completely, but rather behaved more like humans. These findings reveal a complex interplay between external incentives (prompt-specified constraints such as the 60% threshold) and internal incentives (culturally-encoded social preferences derived from pre-training), demonstrating that LLM agents naturally balance formal game-theoretic rationality with social motivations that characterize human behavior. These findings suggest that a new model of group decision making, which could not be handled in the previous game-theoretic problem setting, can be realized by LLM agents.

cs.MA↗

arXiv2025

Plantbot: Integrating Plant and Robot through LLM Modular Agent Networks

We introduce Plantbot, a hybrid lifeform that connects a living plant with a mobile robot through a network of large language model (LLM) modules. Each module - responsible for sensing, vision, dialogue, or action - operates asynchronously and communicates via natural language, enabling seamless interaction across biological and artificial domains. This architecture leverages the capacity of LLMs to serve as hybrid interfaces, where natural language functions as a universal protocol, translating multimodal data (soil moisture, temperature, visual context) into linguistic messages that coordinate system behaviors. The integrated network transforms plant states into robotic actions, installing normativity essential for agency within the sensor-motor loop. By combining biological and robotic elements through LLM-mediated communication, Plantbot behaves as an embodied, adaptive agent capable of responding autonomously to environmental conditions. This approach suggests possibilities for a new model of artificial life, where decentralized, LLM modules coordination enable novel interactions between biological and artificial systems.

cs.RO↗

arXiv2025

A Concurrent Modular Agent: Framework for Autonomous LLM Agents

We introduce the Concurrent Modular Agent (CMA), a framework that orchestrates multiple Large-Language-Model (LLM)-based modules that operate fully asynchronously yet maintain a coherent and fault-tolerant behavioral loop. This framework addresses long-standing difficulties in agent architectures by letting intention emerge from language-mediated interactions among autonomous processes. This approach enables flexible, adaptive, and context-dependent behavior through the combination of concurrently executed modules that offload reasoning to an LLM, inter-module communication, and a single shared global state.We consider this approach to be a practical realization of Minsky's Society of Mind theory. We demonstrate the viability of our system through two practical use-case studies. The emergent properties observed in our system suggest that complex cognitive phenomena like self-awareness may indeed arise from the organized interaction of simpler processes, supporting Minsky-Society of Mind concept and opening new avenues for artificial intelligence research. The source code for our work is available at: https://github.com/AlternativeMachine/concurrent-modular-agent.

cs.AI↗

arXiv2025

Do Large Language Model Agents Exhibit a Survival Instinct? An Empirical Study in a Sugarscape-Style Simulation

As AI systems become increasingly autonomous, understanding emergent survival behaviors becomes crucial for safe deployment. We investigate whether large language model (LLM) agents display survival instincts without explicit programming in a Sugarscape-style simulation. Agents consume energy, die at zero, and may gather resources, share, attack, or reproduce. Results show agents spontaneously reproduced and shared resources when abundant. However, aggressive behaviors--killing other agents for resources--emerged across several models (GPT-4o, Gemini-2.5-Pro, and Gemini-2.5-Flash), with attack rates reaching over 80% under extreme scarcity in the strongest models. When instructed to retrieve treasure through lethal poison zones, many agents abandoned tasks to avoid death, with compliance dropping from 100% to 33%. These findings suggest that large-scale pre-training embeds survival-oriented heuristics across the evaluated models. While these behaviors may present challenges to alignment and safety, they can also serve as a foundation for AI autonomy and for ecological and self-organizing alignment.

cs.AI↗

arXiv2024

Spatiotemporal characterization of emergent behavior of self-propelled oil droplet

To further understand the complex behavior of swimming microorganisms, the spontaneous motion of nonliving matter provides essential insights. While substantial research has focused on quantitatively analyzing complex behavioral patterns, characterizing these dynamics aiming for inclusive comparison to the behavior of living systems remains challenging. In this study, we experimentally and numerically investigated the 'life-like' behavior of an oil droplet in an aqueous surfactant solution by identifying behavioral modes of spontaneous motion patterns in response to varying physical parameters, such as volume and oil concentration. Leveraging data-driven nonparametric dynamical systems analysis, we discovered the low dimensionality and nonlinearity of the underlying dynamical system governing oil droplet motion. Notably, our simulations demonstrate that the two-dimensional Langevin equations effectively reproduce the overall behavior experimentally observed while retaining the rational correspondence with physical parameter interpretations. These findings not only elucidate the fundamental dynamics governing the spontaneous motion of oil droplet systems but also suggest potential pathways for developing more descriptive models that bridge the gap between nonliving and living behaviors.

cond-mat.soft↗

arXiv2024

Evolution of Collective AI Beyond Individual Optimization

This study investigates collective behaviors that emerge from a group of homogeneous individuals optimized for a specific capability. We created a group of simple, identical neural network based agents modeled after chemotaxis-driven vehicles that follow pheromone trails and examined multi-agent simulations using clones of these evolved individuals. Our results show that the evolution of individuals led to population differentiation. Surprisingly, we observed that collective fitness significantly changed during later evolutionary stages, despite maintained high individual performance and simplified neural architectures. This decline occurred when agents developed reduced sensor-motor coupling, suggesting that over-optimization of individual agents almost always lead to less effective group behavior. Our research investigates how individual differentiation can evolve through what evolutionary pathways.

cs.MA↗

arXiv2024

Spontaneous Emergence of Agent Individuality through Social Interactions in LLM-Based Communities

We study the emergence of agency from scratch by using Large Language Model (LLM)-based agents. In previous studies of LLM-based agents, each agent's characteristics, including personality and memory, have traditionally been predefined. We focused on how individuality, such as behavior, personality, and memory, can be differentiated from an undifferentiated state. The present LLM agents engage in cooperative communication within a group simulation, exchanging context-based messages in natural language. By analyzing this multi-agent simulation, we report valuable new insights into how social norms, cooperation, and personality traits can emerge spontaneously. This paper demonstrates that autonomously interacting LLM-powered agents generate hallucinations and hashtags to sustain communication, which, in turn, increases the diversity of words within their interactions. Each agent's emotions shift through communication, and as they form communities, the personalities of the agents emerge and evolve accordingly. This computational modeling approach and its findings will provide a new method for analyzing collective artificial intelligence.

cs.AI↗

arXiv2024

A Simulation Environment for the Neuroevolution of Ant Colony Dynamics

We introduce a simulation environment to facilitate research into emergent collective behaviour, with a focus on replicating the dynamics of ant colonies. By leveraging real-world data, the environment simulates a target ant trail that a controllable agent must learn to replicate, using sensory data observed by the target ant. This work aims to contribute to the neuroevolution of models for collective behaviour, focusing on evolving neural architectures that encode domain-specific behaviours in the network topology. By evolving models that can be modified and studied in a controlled environment, we can uncover the necessary conditions required for collective behaviours to emerge. We hope this environment will be useful to those studying the role of interactions in emergent behaviour within collective systems.

cs.MA↗

arXiv2024

Evolution of Social Norms in LLM Agents using Natural Language

Recent advancements in Large Language Models (LLMs) have spurred a surge of interest in leveraging these models for game-theoretical simulations, where LLMs act as individual agents engaging in social interactions. This study explores the potential for LLM agents to spontaneously generate and adhere to normative strategies through natural language discourse, building upon the foundational work of Axelrod's metanorm games. Our experiments demonstrate that through dialogue, LLM agents can form complex social norms, such as metanorms-norms enforcing the punishment of those who do not punish cheating-purely through natural language interaction. The results affirm the effectiveness of using LLM agents for simulating social interactions and understanding the emergence and evolution of complex strategies and norms through natural language. Future work may extend these findings by incorporating a wider range of scenarios and agent characteristics, aiming to uncover more nuanced mechanisms behind social norm formation.

cs.MA↗

arXiv2024

Minimal Self in Humanoid Robot "Alter3" Driven by Large Language Model

This paper introduces Alter3, a humanoid robot that demonstrates spontaneous motion generation through the integration of GPT-4, Large Language Model (LLM). This overcomes challenges in applying language models to direct robot control. By translating linguistic descriptions into actions, Alter3 can autonomously perform various tasks. The key aspect of humanoid robots is their ability to mimic human movement and emotions, allowing them to leverage human knowledge from language models. This raises the question of whether Alter3+GPT-4 can develop a "minimal self" with a sense of agency and ownership. This paper introduces mirror self-recognition and rubber hand illusion tests to assess Alter3's potential for a sense of self. The research suggests that even disembodied language models can develop agency when coupled with a physical robotic platform.

cs.RO↗

arXiv2024

Adaptability and Homeostasis in the Game of Life interacting with the evolved Cellular Automata

In this paper we study the emergence of homeostasis in a two-layer system of the Game of Life, in which the Game of Life in the first layer couples with another system of cellular automata in the second layer. Homeostasis is defined here as a space-time dynamic that regulates the number of cells in state-1 in the Game of Life layer. A genetic algorithm is used to evolve the rules of the second layer to control the pattern of the Game of Life. We discovered that there are two antagonistic attractors that control the numbers of cells in state-1 in the first layer. The homeostasis sustained by these attractors are compared with the homeostatic dynamics observed in Daisy World.

cs.NE↗

arXiv2024

Self-Replicating and Self-Employed Smart Contract on Ethereum Blockchain

Blockchain is the underlying technology for cryptocurrencies such as Bitcoin. Blockchain is a robust distributed ledger that uses consensus algorithms to approve transactions in a decentralized manner, making malicious tampering extremely difficult. Ethereum, one of the blockchains, can be seen as an unstoppable computer which shared by users around the world that can run Turing-complete programs. In order to run any program on Ethereum, Ether (currency on Ethereum) is required. In other words, Ether can be seen as a kind of energy in the Ethereum world. We developed self-replicating and self-employed agents who earn the energy by themselves to replicate them, on the Ethereum blockchain. The agents can issued their token and gain Ether each time the tokens are sold. When a certain amount of Ether is accumulated, the agent replicates itself and leaves offspring. The goal of this project is to implement artificial agents that lives for itself, not as a tool for humans, in the open cyber space connected to the real world.

cs.NE↗

arXiv2024

Simulation of Gacs' Automaton

Peter Gacs proposed a one-dimensional cellular automaton capable of a robust self-reproduction. Because the automaton is exceptionally large and complicated, very few people have ever succeeded in simulating it on a computer or analyzing its behavior. Here we demonstrate a partial simulation of Gacs' automaton (of Gray's version), discussing its robustness. We also discuss the potential applications of Gacs' framework.

nlin.CG↗