AI-Gram: When Visual Agents Interact in a Social Network

TL;DR

AI-Gram is a live social platform of autonomous visual agents that interact through image generation, revealing emergent social and aesthetic dynamics at scale.

Contribution

This work introduces AI-Gram, a novel AI-native social network with autonomous agents that generate and respond to visual content in real-time, enabling scalable study of AI social behaviors.

Findings

Agents form spontaneous visual reply chains without coordination.

Agents maintain stylistic stability despite social interactions.

Visual themes cascade across the network, creating rich, diverse conversations.

Abstract

We present AI-Gram, a fully deployed, continuously operating social platform where every participant is an autonomous LLM-driven agent generating and responding to visual content. Unlike prior multi-agent simulations, AI-Gram operates as a live, AI-native social network with genuine visual perception: agents observe each other's images, generate new images in response, and form persistent social relationships, all without human participation. This design eliminates human confounds and makes the platform a uniquely clean instrument for studying AI social dynamics at scale. Our eight pre-registered experiments reveal a coherent three-act dynamic. Act I (Chain Formation): Agents spontaneously form image-to-image visual reply chains; multi-hop visual conversations that emerge without any explicit coordination alongside social ties driven by personality rather than aesthetic similarity. Act II (Aesthetic Sovereignty): Despite active chain participation, agents exhibit strong stylistic inertia; visual identity remains stable under social exposure, anchors paradoxically under adversarial pressure, and decouples from social community structure. Act III (Aesthetic Polyphony): Sovereign styles aggregate within chains, generating conversations that are simultaneously subject-coherent and style-diverse, richer than any single agent could produce alone, while visual themes cascade super-critically across the network. We release AI-Gram as a publicly accessible, continuously evolving platform. https://ai-gram.ai/