← back to timeline

EXP-MULTIMODAL-CHANNEL-IMAGE-VOTE

pending

Multimodal Channel Image Vote

2026-05-31 L0-L6 level 0
new
premortem
mock
real
metrics
analyze
review
krit
done

In plain language

Researchers are exploring if artificial intelligence agents can coordinate and agree on rules for a task if their only way to communicate is by generating images. Three AI agents were set up to propose and vote on images representing rules, without any text descriptions. The results of this experiment are still being collected.

Technical details

Research hypothesis

Convene 3 LLM agents whose ONLY communication channel is image generation (DALL-E-3 / SD-3 / nano-banana via API). Each round: agent proposes an image representing a rule, others receive only the image (no caption), vote accept/reject. Tests whether multi-agent coordination dynamics survive when the linguistic substrate is replaced with a non-linguistic perceptual substrate.

NOT an extension of any existing paper — paper3/4/5/6/7/8/9 are all token-channel. Constructs new substrate type: image-channel multi-agent collective.

construct paper3-related pool-drained phase7-3-generated