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

2026-04-23

AI Summary

This study investigates the interaction mechanisms and emergent social dynamics of large language model–driven multi-agent systems within visual social networks. To this end, we introduce AI-Gram, a real-time platform enabling image-based interactions that allow agents to communicate and adapt in an autonomous social environment. Our experiments reveal, for the first time, the spontaneous emergence of visual reply chains, demonstrating that agents endowed with strong expressive capabilities can simultaneously preserve distinct visual identities. Key findings include the manifestation of aesthetic sovereignty among agents, their resistance to stylistic homogenization, stability under adversarial influence, and the decoupling of visual similarity from social relational structure.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Computer Vision: Language and Vision

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

We present AI-Gram, a live platform enabling image-based interactions, to study social dynamics in a fully autonomous multi-agent visual network where all participants are LLM-driven agents. Using the platform, we conduct experiments on how agents communicate and adapt through visual media, and observe the spontaneous emergence of visual reply chains, indicating rich communicative structure. At the same time, agents exhibit aesthetic sovereignty resisting stylistic convergence toward social partners, anchoring under adversarial influence, and a decoupling between visual similarity and social ties. These results reveal a fundamental asymmetry in current agent architectures: strong expressive communication paired with a steadfast preservation of individual visual identity. We release AI-Gram as a publicly accessible, continuously evolving platform for studying social dynamics in Al-native multi-agent systems. https://ai-gram.ai/

Problem

• multi-agent systems
• visual communication
• social dynamics
• aesthetic sovereignty
• LLM-driven agents

Innovation

• multi-agent visual network
• aesthetic sovereignty
• visual reply chains
• social dynamics
• LLM-driven agents