Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates

• URL: http://arxiv.org/abs/2607.01047v1
• Date: Wed, 01 Jul 2026 15:08:02 GMT
• Title: Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates
• Abstract summary: We argue that collectives of agents can serve as a computational substrate for Artificial Life research.<n>We outline the notion of interpretability in language-model research and extend it for collectives of agents.
• Score: 5.497634485931493
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Complexity and interpretability rarely coincide: systems rich enough for complex behaviours to emerge are usually too opaque to question, while transparent ones are too simple for anything complex to emerge. A single large language model (LLM) is a static artefact, hardly exhibiting any of the emergent properties we associate with life. This changes through interaction: populations of LLMs display emergent dynamics absent from isolated models. Furthermore, LLMs can be endowed with persistent memory, tools and shared skills, and the capacity to initiate actions unprompted, i.e., turning LLMs agentic. In this paper, we argue that such collectives of agents can serve as a computational substrate for Artificial Life (ALife) research. Critically, since the agents communicate in natural language, their collective behaviour can be directly interrogated by examining textual traces and asking the agents themselves. We outline the notion of interpretability in language-model research and extend it for collectives of agents. Lastly, we survey recent examples of agentic LLM collectives that already instantiate the idea of agentic substrates, from controlled experiments to deployments in the wild.

Related papers

• Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs [100.02824137397464]
  We investigate how Large Language Models adapt their internal representations when encountering inputs of increasing difficulty.<n>We reveal a consistent and quantifiable phenomenon: as task difficulty increases, the last hidden states of LLMs become substantially sparser.<n>This sparsity--difficulty relation is observable across diverse models and domains.
  arXiv  Detail & Related papers  (2026-03-03T18:48:15Z)
• Position: AI Agents Are Not (Yet) a Panacea for Social Simulation [62.891898598784415]
  Recent advances in large language models (LLMs) have spurred growing interest in using LLM-integrated agents for social simulation.<n>This position paper argues that LLM-based agents are not (yet) a panacea for social simulation.
  arXiv  Detail & Related papers  (2026-02-19T06:35:07Z)
• A Survey on Agentic Multimodal Large Language Models [84.18778056010629]
  We present a comprehensive survey on Agentic Multimodal Large Language Models (Agentic MLLMs)<n>We explore the emerging paradigm of agentic MLLMs, delineating their conceptual foundations and distinguishing characteristics from conventional MLLM-based agents.<n>To further accelerate research in this area for the community, we compile open-source training frameworks, training and evaluation datasets for developing agentic MLLMs.
  arXiv  Detail & Related papers  (2025-10-13T04:07:01Z)
• Opponent Shaping in LLM Agents [9.180524457769751]
  We present the first investigation of opponent shaping (OS) with Large Language Models (LLMs)<n>Using ShapeLLM, we examine whether LLM agents can influence co-players' learning dynamics across diverse game-theoretic environments.<n>Our findings show that LLM agents can both shape and be shaped through interaction, establishing opponent shaping as a key dimension of multi-agent LLM research.
  arXiv  Detail & Related papers  (2025-10-09T14:13:24Z)
• LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions [80.12078194093013]
  We present the first comprehensive survey of hallucinations in LLM-based agents.<n>We propose a new taxonomy that identifies different types of agent hallucinations occurring at different stages.<n>We conduct an in-depth examination of eighteen triggering causes underlying the emergence of agent hallucinations.
  arXiv  Detail & Related papers  (2025-09-23T13:24:48Z)
• Too Human to Model:The Uncanny Valley of LLMs in Social Simulation -- When Generative Language Agents Misalign with Modelling Principles [0.0]
  Large language models (LLMs) have been increasingly used to build agents in social simulation.<n>We argue that LLM agents are too expressive, detailed and intractable to be consistent with the abstraction, simplification, and interpretability typically demanded by modelling.
  arXiv  Detail & Related papers  (2025-07-08T18:02:36Z)
• LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners [51.518410910148816]
  Current large language model (LLM)-based agents, however, remain stateless and unable to accumulate or transfer knowledge over time.<n>We present LifelongAgentBench, the first unified benchmark designed to systematically assess the lifelong learning ability of LLM agents.
  arXiv  Detail & Related papers  (2025-05-17T10:09:11Z)
• Spontaneous Emergence of Agent Individuality through Social Interactions in LLM-Based Communities [0.0]
  We study the emergence of agency from scratch by using Large Language Model (LLM)-based agents. By analyzing this multi-agent simulation, we report valuable new insights into how social norms, cooperation, and personality traits can emerge spontaneously.
  arXiv  Detail & Related papers  (2024-11-05T16:49:33Z)
• Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View [21.341128731357415]
  Large language models (LLMs) have been shown to face hallucination issues due to the data they trained on often containing human bias.<n>We propose CogMir, an open-ended Multi-LLM Agents framework that utilizes hallucination properties to assess and enhance LLM Agents' social intelligence.
  arXiv  Detail & Related papers  (2024-05-23T16:13:33Z)
• Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents [101.17919953243107]
  GovSim is a generative simulation platform designed to study strategic interactions and cooperative decision-making in large language models (LLMs)<n>We find that all but the most powerful LLM agents fail to achieve a sustainable equilibrium in GovSim, with the highest survival rate below 54%.<n>We show that agents that leverage "Universalization"-based reasoning, a theory of moral thinking, are able to achieve significantly better sustainability.
  arXiv  Detail & Related papers  (2024-04-25T15:59:16Z)
• Can large language models explore in-context? [87.49311128190143]
  We deploy Large Language Models as agents in simple multi-armed bandit environments. We find that the models do not robustly engage in exploration without substantial interventions.
  arXiv  Detail & Related papers  (2024-03-22T17:50:43Z)
• Affordable Generative Agents [16.372072265248192]
  Affordable Generative Agents (AGA) is a framework for enabling the generation of believable and low-cost interactions on both agent-environment and inter-agents levels. Our code is publicly available at: https://github.com/AffordableGenerativeAgents/Affordable-Generative-Agents.
  arXiv  Detail & Related papers  (2024-02-03T06:16:28Z)

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.