SwarmWorld: Stigmergic technological evolution in societies of language-model agents
cs.AI, cond-mat.mtrl-sci, cs.CL
Submitted: 2026-08-26
Updated: 2026-08-26
Code: https://github.com/lamm-mit/SwarmWorld
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: Collective intelligence can emerge when individuals coordinate through a shared environment, allowing local actions to accumulate into durable social organization.
Terminology
Abstract
Collective intelligence can emerge when individuals coordinate through a shared environment, allowing local actions to accumulate into durable social organization. Language-model agents offer a new substrate for this process, yet most multi-agent systems rely on direct conversation, predefined roles, or centralized workflows. It remains unclear whether decentralized agents can build functional technologies and outperform independent search. Here, initially homogeneous LLM agents in SwarmWorld self-organize without assigned roles or recipes into evolving technological societies. Agents explore a spatial environment, process resources, test materials, construct persistent artifacts, and write executable controllers evaluated by a deterministic simulator under unseen disturbances after the agents are removed. SwarmWorld splits cognition from consequence: agents propose architectures and controllers within fixed action and material schemas, while the simulated world determines function. Shared societies develop broader, more resilient technological portfolios than a strong best-of-N isolated-search baseline, although isolated search remains competitive for the strongest artifact. Agents differentiate into exploration, construction, maintenance, and coordination behaviors, transitioning as the world matures. Technologies accumulate through collaborative construction, executable inheritance, and persistent agent-artifact networks, with most reuse beginning through physical observation rather than communication. Explicit cultural mechanisms amplify collaboration and organization, but functional benefits depend on outcome and timescale. Physical stigmergy alone supports capable societies, while interaction drives persistent technological ecologies rather than universally superior individual inventions.
Sources
- LLM2Swarm: Robot Swarms that Responsively Reason, Plan, and Collaborate through LLMs
- Generative Agents: Interactive Simulacra of Human Behavior
- Project Sid: Many-agent simulations toward AI civilization
- AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society
- TerraLingua: Emergence and Analysis of Open-endedness in LLM Ecologies
- Emergent Tool Use From Multi-Agent Autocurricula
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Benchmarking LLMs' Swarm intelligence
- Sparks: Multi-Agent Artificial Intelligence Model Discovers Protein Design Principles
- CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution
- LLM Agent Swarm for Hypothesis-Driven Drug Discovery
- An Agentic AI Scientific Community for Automated Neural Operator Discovery
- Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange
- Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection