arXiv cs.MA· Shanghao Shi, Jian Xiao, Ching-Hsiang Chan, Sanjoy Baruah, Sastry Kompella, Yevgeniy Vorobeychik, William Yeoh, Ning Zhang·· 11 小时前AI 评分31
SCALE：面向信息物理智能体的实时潜在通信方法
SCALE: Real-Time Latent Communication for Cyber-Physical Agents
AI 导读
SCALE 是一种面向信息物理智能体的实时潜在通信方法，通过相似度匹配连续潜在消息中的 token 以复用信息、避免冗余传输，并依据语义增益与通信成本调度待发消息及潜在 token 数量。在三个信息物理基准和蜘蛛机器人案例中，SCALE 在带宽受限网络下显著提升了任务性能与按时交付率。代码已开源。
正文 · 原文
Abstract:Latent communication enables agents to collaborate efficiently by directly exchanging intermediate model representations rather than raw sensor data or text messages. Existing approaches, however, are primarily designed for LLM agents and do not consider the bandwidth constraints and heterogeneous task deadlines faced by cyber-physical agents. In this work, we propose SCALE, a real-time latent communication method tailored for cyber-physical agents. Motivated by the spatio-temporal continuity of the physical world, SCALE matches tokens across consecutive latent messages using similarity scores to identify reusable information and avoid redundant transmission. It then profiles the semantic gain and communication cost of transmitting different amounts of latent information. Based on these profiles, SCALE employs a real-time scheduler that jointly determines which pending messages to transmit and how many latent tokens to send, subject to available bandwidth and task deadlines. We evaluate SCALE across three cyber-physical benchmarks and a physical spider robot case study under diverse network conditions and heterogeneous task deadlines. Our results show that SCALE significantly improves both task performance and on-time delivery in bandwidth-constrained networks. Our code is available at: this https URL.
| Subjects: | Robotics (cs.RO); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2611.08390 [cs.RO] |
| (or arXiv:2611.08390v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08390 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shanghao Shi [view email]
[v1]
Thu, 5 Nov 2026 18:05:58 UTC (9,107 KB)
来源：arXiv cs.MA · arxiv.org