Multiagent AI systems require consistent communication, but we lack methods to verify that agents share the same understanding of the terms used. Natural language is interpretable but vulnerable to semantic drift, while learned protocols are efficient but opaque. We propose a certification protocol based on the stimulus-meaning model, where agents are tested on shared observable events and terms are certified if empirical disagreement falls below a statistical threshold. In this protocol, agents restricting their reasoning to certified terms ("core-guarded reasoning") achieve provably bounded disagreement. We also outline mechanisms for detecting drift (recertification) and recovering shared vocabulary (renegotiation). In simulations with varying degrees of semantic divergence, core-guarding reduces disagreement by 72-96%. In a validation with fine-tuned language models, disagreement is reduced by 51%. Our framework provides a first step towards verifiable agent-to-agent communication.
GeoContra: From Fluent GIS Code to Verifiable Spatial Analysis with Geography-Grounded Repair
School of Big Data and Artificial Intelligence, Guangdong University of Finance and Economics(大数据与人工智能学院,广东财经大学);School of Geography and Environment Economics, Guangdong University of Finance & Economics(地理与环境经济学院,广东财经大学);Guangdong Engineering Research Center of Low-Altitude Remote Sensing Intelligent Monitoring(低空遥感智能监测工程研究中心)
National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China(电子科技大学无线通信国家重点实验室);Department of Electronic Engineering, Tsinghua University(清华大学电子工程系)
Knowledge Base Enabled Semantic Communication: A Generative Perspective
Shenzhen Future Network of Intelligence Institute (FNii-Shenzhen)(深圳未来智能网络研究院(深圳FNii));School of Science and Engineering (SSE)(科学与工程学院);The Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳));Peng Cheng Laboratory(鹏城实验室);Beijing University of Posts and Telecommunications(北京邮电大学)
Less Data, More Knowledge: Building Next Generation Semantic Communication Networks
Virginia Tech(弗吉尼亚理工大学);Technology Innovation Institute(技术创新研究院);CentraleSupelec(巴黎中央理工-高等电力学院);University Paris-Saclay(巴黎萨克雷大学);University of Houston(休斯顿大学);Kyung Hee University(庆熙大学);Princeton University(普林斯顿大学)