English

Project Sid: Many-agent simulations toward AI civilization

Artificial Intelligence 2024-11-04 v1 Multiagent Systems

Abstract

AI agents have been evaluated in isolation or within small groups, where interactions remain limited in scope and complexity. Large-scale simulations involving many autonomous agents -- reflecting the full spectrum of civilizational processes -- have yet to be explored. Here, we demonstrate how 10 - 1000+ AI agents behave and progress within agent societies. We first introduce the PIANO (Parallel Information Aggregation via Neural Orchestration) architecture, which enables agents to interact with humans and other agents in real-time while maintaining coherence across multiple output streams. We then evaluate agent performance in agent simulations using civilizational benchmarks inspired by human history. These simulations, set within a Minecraft environment, reveal that agents are capable of meaningful progress -- autonomously developing specialized roles, adhering to and changing collective rules, and engaging in cultural and religious transmission. These preliminary results show that agents can achieve significant milestones towards AI civilizations, opening new avenues for large simulations, agentic organizational intelligence, and integrating AI into human civilizations.

Keywords

Cite

@article{arxiv.2411.00114,
  title  = {Project Sid: Many-agent simulations toward AI civilization},
  author = {Altera. AL and Andrew Ahn and Nic Becker and Stephanie Carroll and Nico Christie and Manuel Cortes and Arda Demirci and Melissa Du and Frankie Li and Shuying Luo and Peter Y Wang and Mathew Willows and Feitong Yang and Guangyu Robert Yang},
  journal= {arXiv preprint arXiv:2411.00114},
  year   = {2024}
}

Comments

35 pages, 14 figures

R2 v1 2026-06-28T19:43:30.393Z