| title | Hidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication |
|---|---|
| authors | Alan-Barsag Gazzaev, Alexey Gavrilov, Sergey Muravyov, Ilya Makarov |
| date | 2026-10-20 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.28905 |
| affiliation | ITMO University |
| upvotes | 14 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Diffusion language models form answers through a sequence of revisable continuous states, but multi-agent systems usually discard those states and make agents communicate only after decoding text. We ask whether one independent diffusion trajectory can pass a compact hidden message into another and, crucially, whether the receiver uses what that message means. In Hidden Messages, a sender compresses its denoising state into four signed dense vectors; the receiver consumes them while retaining its own context, canvas, and trajectory. Removing a message tests whether the channel matters; replacing it with a message from another example tests whether its content matters. Across controlled tasks, derangement removes a +63.6-point advantage on Tiny-A2D and a +100.0-point advantage on Dream-7B, while targeted substitutions steer the receiver toward the substituted fact. On QASC with the two supporting facts split across agents, matched communication reaches 80.8%, but a wrong-example message lowers accuracy to 46.8%, a content effect of +34.0 points. The surprising result is temporal: one late transfer reaches 87.8%, exceeding four recurrent exchanges by +7.0 points. These experiments provide causal evidence for continuous hidden communication between diffusion-LM agents and show that when information is transferred can matter more than how many times agents exchange it. |
cite
@misc{gazzaev2026hidden,
title={Hidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication},
author={Alan-Barsag Gazzaev and Alexey Gavrilov and Sergey Muravyov and Ilya Makarov},
year={2026},
eprint={2610.28905},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.28905}
}