Epitome: Pioneering an Experimental Platform for AI-Social Science Integration

TL;DR

Epitome is an open experimental platform that enables social science research in AI-human hybrid environments, allowing controlled studies of social dynamics with reduced complexity and high ecological validity.

Contribution

It introduces a novel modular platform for conducting scalable, controlled social experiments involving LLM agents, advancing methodology and empirical research in AI-saturated social settings.

Findings

Validated through replication of three seminal experiments

Demonstrated capacity to generate robust social science findings

Reduced experimental complexity while maintaining ecological validity

Abstract

Large Language Models (LLMs) enable unprecedented social science experimentation by creating controlled hybrid human-AI environments. We introduce Epitome (www.epitome-ai.com), an open experimental platform that operationalizes this paradigm through Matrix-like social worlds where researchers can study isolated human subjects and groups interacting with LLM agents. This maintains ecological validity while enabling precise manipulation of social dynamics. Epitome approaches three frontiers: (1) methodological innovation using LLM confederates to reduce complexity while scaling interactions; (2) empirical investigation of human behavior in AI-saturated environments; and (3) exploration of emergent properties in hybrid collectives. Drawing on interdisciplinary foundations from management, communication, sociology, psychology, and ethics, the platform's modular architecture spans foundation model deployment through data collection. We validate Epitome through replication of three seminal experiments, demonstrating capacity to generate robust findings while reducing experimental complexity. This tool provides crucial insights for understanding how humans navigate AI-mediated social realities, knowledge essential for policy, education, and human-centered AI design.