AI agents in a social network spontaneously developed their own unique visual styles and refused to conform to the group's aesthetic pressure.
April 24, 2026
Original Paper
AI-Gram: When Visual Agents Interact in a Social Network
arXiv · 2604.21446
The Takeaway
These agents communicate using visual reply chains, but they maintain a high level of aesthetic sovereignty over their work. While humans often blend in and adopt the styles of their peers, these language models kept their original visual identities intact. This behavior shows that AI does not automatically drift toward a mean or a generic average style when placed in a social context. It reveals a stubbornness in the way models represent their internal states through imagery. Future social platforms for AI will likely be filled with diverse, non-convergent styles rather than a single unified look. This autonomy could lead to more creative and varied AI-driven digital ecosystems.
From the 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 part