Emergent Culture in Minimal LLM Systems

• URL: http://arxiv.org/abs/2606.30668v1
• Date: Sun, 21 Jun 2026 15:56:36 GMT
• Title: Emergent Culture in Minimal LLM Systems
• Abstract summary: Inspired by swarm engineering, we give collectives of three agents the ability to send messages and manipulate a shared text store.<n>Using tools from dynamical systems analysis, we show that these behaviours exhibit structured long-range coherence beyond the entropy horizon of the decaying store.
• Score: 0.4640835690336653
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: What happens when LLM agents operate with no context outside a turn, minimal prompting, and simple tools? Inspired by swarm engineering, we give collectives of three agents the ability to send messages and manipulate a shared actively decaying text store, introducing evolutionary pressure. The agents spontaneously cooperate, develop storage management strategies, and generate complex evolving cultural artifacts, with no top-down engineering. Using tools from dynamical systems analysis, we show that these behaviours exhibit structured long-range coherence beyond the entropy horizon of the decaying store, consistent with emergent culture in the Sperberian sense.

Related papers

• Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence [115.91847478507736]
  LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks.<n>Many tasks require heterogeneous expertise, interdependent subtasks, parallel execution, independent verification, and persistent state.<n>We call this System Intelligence: an agent system's ability to organize and coordinate multiple intelligent components into a coherent, adaptive whole.
  arXiv  Detail & Related papers  (2026-08-21T14:27:57Z)
• Loosely-Structured Software: Engineering Context, Structure, and Evolution Entropy in Runtime-Rewired Multi-Agent Systems [9.34019956999278]
  Building robust multi-agent systems requires engineering discipline focused on architecture to manage complexity under uncertainty.<n>This paper introduces emphLoosely-Structured Software (LSS), a new class of software systems that shifts the engineering focus from constructing deterministic logic to managing the runtime entropy.
  arXiv  Detail & Related papers  (2026-03-16T02:07:34Z)
• Expanding LLM Agent Boundaries with Strategy-Guided Exploration [51.98616048282804]
  Reinforcement learning (RL) has demonstrated notable success in post-training large language models (LLMs) as agents for tasks such as computer use, tool calling, and coding.<n>We propose Strategy-Guided Exploration (SGE) to shift exploration from low-level actions to higher-level language strategies.
  arXiv  Detail & Related papers  (2026-03-02T16:28:39Z)
• Self-Consolidation for Self-Evolving Agents [51.94826934403236]
  Large language model (LLM) agents operate as static systems, lacking the ability to evolve through lifelong interaction.<n>We propose a novel self-evolving framework for LLM agents that introduces a complementary evolution mechanism.
  arXiv  Detail & Related papers  (2026-02-02T11:16:07Z)
• Monadic Context Engineering [59.95390010097654]
  This paper introduces Monadic Context Engineering (MCE) to provide a formal foundation for agent design.<n>We demonstrate how Monads enable robust composition, how Applicatives provide a principled structure for parallel execution, and crucially, how Monad Transformers allow for the systematic composition of these capabilities.<n>This layered approach enables developers to construct complex, resilient, and efficient AI agents from simple, independently verifiable components.
  arXiv  Detail & Related papers  (2025-12-27T01:52:06Z)
• Sophia: A Persistent Agent Framework of Artificial Life [28.114645157988658]
  Sophia is a "Persistent Agent" wrapper that grafts a continuous self-improvement loop onto any LLM-centric System 1/2 stack.<n>It is driven by four synergistic mechanisms: process-supervised thought search, narrative memory, user and self modeling, and a hybrid reward system.<n>It independently initiates and executes various tasks while achieving an 80% reduction in reasoning steps for recurring operations.
  arXiv  Detail & Related papers  (2025-12-20T03:56:09Z)
• Don't lie to your friends: Learning what you know from collaborative self-play [63.0121884175594]
  We propose a radically new approach to teaching AI agents what they know.<n>We construct multi-agent collaborations in which the group is rewarded for collectively arriving at correct answers.<n>The desired meta-knowledge emerges from the incentives built into the structure of the interaction.
  arXiv  Detail & Related papers  (2025-03-18T17:53:20Z)
• MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning [2.601143512330214]
  Embodied agents powered by large language models (LLMs) promise open-ended competence in worlds such as Minecraft.<n>We propose MindForge, a generative-agent framework for cultural lifelong learning through explicit perspective taking.
  arXiv  Detail & Related papers  (2024-11-20T02:10:44Z)
• Compromising Embodied Agents with Contextual Backdoor Attacks [69.71630408822767]
  Large language models (LLMs) have transformed the development of embodied intelligence. This paper uncovers a significant backdoor security threat within this process. By poisoning just a few contextual demonstrations, attackers can covertly compromise the contextual environment of a black-box LLM.
  arXiv  Detail & Related papers  (2024-08-06T01:20:12Z)
• Transforming Agency. On the mode of existence of Large Language Models [0.0]
  This paper investigates the ontological characterization of Large Language Models (LLMs) like ChatGPT. We argue that ChatGPT should be characterized as an interlocutor or linguistic automaton, a library-that-talks, devoid of (autonomous) agency.
  arXiv  Detail & Related papers  (2024-07-15T14:01:35Z)
• Procedural Adherence and Interpretability Through Neuro-Symbolic Generative Agents [0.9886108751871757]
  We propose a combination of formal logic-based program synthesis and LLM content generation to bring guarantees of procedural adherence and interpretability to generative agent behavior. To illustrate the benefit of procedural adherence and interpretability, we use Temporal Stream Logic (TSL) to generate an automaton that enforces an interpretable, high-level temporal structure on an agent.
  arXiv  Detail & Related papers  (2024-02-24T21:36:26Z)
• Octopus: Embodied Vision-Language Programmer from Environmental Feedback [58.04529328728999]
  Embodied vision-language models (VLMs) have achieved substantial progress in multimodal perception and reasoning. To bridge this gap, we introduce Octopus, an embodied vision-language programmer that uses executable code generation as a medium to connect planning and manipulation. Octopus is designed to 1) proficiently comprehend an agent's visual and textual task objectives, 2) formulate intricate action sequences, and 3) generate executable code.
  arXiv  Detail & Related papers  (2023-10-12T17:59:58Z)

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.