[2411.00114] Project Sid: Many-agent simulations toward AI civilization
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.
# link_1tot0kxjh3e.pdf ## Metadata - PDFFormatVersion=1.5 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - CreationDate=D:20241104010435Z - Creator=LaTeX with hyperref - ModDate=D:20241104010435Z - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) kpathsea version 6.3.5 - Producer=pdfTeX-1.40.25 - Trapped=False ## Contents ### Page 1 Project Sid: Many-agent simulations toward AI civilizationAltera.AL1science@altera.alAI agents have been evaluated in isolation or within small gro
saved by
related reading
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- Patterns and problems in multiagent systemsanthropic.com
- [2502.14143] Multi-Agent Risks from Advanced AIarxiv.org
- [2410.00079] Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interfacearxiv.org
- Generative Agent Simulations of 1,000 Peopleantephase.com
- [2603.11214] Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenariosarxiv.org
- [2501.10114] Infrastructure for AI Agentsarxiv.org
- [2605.10310] Positive Alignment: Artificial Intelligence for Human Flourishingarxiv.org
- [2502.15657] Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?arxiv.org
- Of Swarms and Sand Godsblog.cosmos-institute.org
- [2603.24676] When Is Collective Intelligence a Lottery? Multi-Agent Scaling Laws for Memetic Drift in LLMsarxiv.org