# SwarmWorld: Stigmergic technological evolution in societies of language-model agents

arXiv: https://arxiv.org/abs/2608.26081 · HTML: https://mlsanity.com/paper/2608.26081/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 64 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 14 of 14)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents](https://mlsanity.com/paper/2406.06769/) (2024)
- [Project Sid: Many-agent simulations toward AI civilization](https://mlsanity.com/paper/2411.00114/) (2024)
- [CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution](https://mlsanity.com/paper/2512.23880/) (2025)
- [Sparks: Multi-Agent Artificial Intelligence Model Discovers Protein Design Principles](https://mlsanity.com/paper/2504.19017/) (2025)
- [LLM2Swarm: Robot Swarms that Responsively Reason, Plan, and Collaborate through LLMs](https://mlsanity.com/paper/2410.11387/) (2024)
- [Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange](https://mlsanity.com/paper/2603.14312/) (2026)
- [LLM Agent Swarm for Hypothesis-Driven Drug Discovery](https://mlsanity.com/paper/2504.17967/) (2025)
- [Benchmarking LLMs' Swarm intelligence](https://mlsanity.com/paper/2505.04364/) (2025)
- [TerraLingua: Emergence and Analysis of Open-endedness in LLM Ecologies](https://mlsanity.com/paper/2603.16910/) (2026)
- [Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence](https://mlsanity.com/paper/2606.01444/) (2026)
- [An Agentic AI Scientific Community for Automated Neural Operator Discovery](https://mlsanity.com/paper/2607.12122/) (2026)

## Built on by (most cited first, 4 of 4)

- [Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent Memory](https://mlsanity.com/paper/2609.03340/) (2026)
- [Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions](https://mlsanity.com/paper/2609.06140/) (2026)
- [We Built a Mirror and Mistook It for a Mind: Causal Liability and the Fallacy of AI Consciousness](https://mlsanity.com/paper/2609.06715/) (2026)
- [LEGIT: Credentialing Protocol for Trustworthy AI Agent Marketplaces](https://mlsanity.com/paper/2609.21325/) (2026)

## Abstract (arXiv)

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.