arXiv 2610.28905 · cs.AI · 2026-10-20
Hidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication
Alan-Barsag Gazzaev, Alexey Gavrilov, Sergey Muravyov, Ilya Makarov
ITMO University
In latest · #384 Added on 2026-10-26
One-line takeaway
Diffusion LM agents can pass compact hidden messages (four dense vectors from the denoising state); deranging the messages erases a +63.6-point advantage on Tiny-A2D and +100 points on Dream-7B, showing the receiver uses their content.
论文验证扩散语言模型智能体之间能用隐向量传递信息：发送方把去噪状态压成 4 个向量交给接收方；打乱消息后，Tiny-A2D 上 +63.6 分、Dream-7B 上 +100 分的优势消失。
Read on arXiv PDF Hugging Face discussion Code
Topics & disciplines
More on Agents
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲388
- Player-1: Learning to Play from Synthetic Experience ▲347
More on LLMs
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.