跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-20AI 評分51

擴散語言模型智能體之間的隱藏訊息:潛在溝通的因果證據

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

AI 導讀

研究指出,擴散語言模型智能體可透過壓縮的連續隱藏訊息影響另一智能體的推理,且傳遞時機有時比反覆交換更重要。QASC 任務中,兩項支持事實分由兩個智能體掌握時,匹配訊息使準確率達 80.8%,錯誤樣本訊息則降至 46.8%,相差 34.0 個百分點。一次較晚傳遞達 87.8%,比四次循環交換高 7.0 個百分點。

正文

Published on Oct 20

Authors:

,

,

Abstract

Diffusion language model agents can exchange compressed continuous hidden messages that causally affect reasoning, with the timing of transfer sometimes outweighing repeated exchanges.

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.

View arXiv page View PDF GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.28905

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.28905 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.28905 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.28905 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co