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
在最新榜 #384 本站收录于 2026-10-26
一句话要点
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。
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.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
主题与学科
同主题：智能体
- 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
同主题：大语言模型
- 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
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。