A Heart Means Recursion: Exploring Visual Meaning and Communication in VLMs

arXiv cs.AIOctober 28, 2026en

arXiv:2610.36449v1 Announce Type: new Abstract: Do vision-language models (VLMs) share our ability to communicate visually? We share preliminary findings, starting from a surprising observation: simple visual symbols like a red heart can strongly influence model behavior on seemingly unrelated tasks, such as steering models towards recursive solutions on simple coding problems. Notably, this steering effect is largely implicit, as models' direct interpretations and thinking traces about visual symbols diverge substantially from their observed behavior. In visual communication between models, this leads to a generation--interpretation gap: while models tend to send shape primitives that they

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning