Hidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication

arXiv:2610.28905v1 Announce Type: new 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.

Shows hidden communication between AI agents, potentially improving cooperation, but lacks societal context.

The paper demonstrates a technical capability for latent communication between diffusion language model agents, which may improve multi-agent coordination. However, the direct societal implications for human flourishing are unclear and speculative based on current evidence. The result concerns AI communication internal processes, not direct human impact.

SOURCE     arXiv cs.AI (tier 1)
   ↓
DOCUMENT   f72bd903-c6b7-44d7-98a2-a5643a03e27f
           https://arxiv.org/abs/2610.28905
   ↓
EVIDENCE   3 extracted excerpts
   ↓
MODEL RUN  4 runs, methodology 1.0.1
   ↓
SCORE      -37  (Adverse)
   ↓
CONFIDENCE 50%