Goal-Oriented Multi-Agent Semantic Networking: Unifying Intents, Semantics, and Intelligence

TL;DR

The paper tackles the mismatch between legacy networks and the goal-driven requirements of 6G services by introducing GoAgentNet, a four-layer, multi-agent semantic architecture that enables cross-layer, goal-oriented collaboration through semantic computation. It details the Application, Agent, Knowledge, and Network layers, along with agent types, protocols, knowledge graphs, and cross-layer feedback mechanisms, to translate high-level intents into actionable plans across domains. Key contributions include a comprehensive architectural design, explicit enablers, use-case demonstrations (robotic fault detection and recovery, VQA, and 3D video generation), and proposed solutions for deployment challenges such as intent-action mapping, orchestration, and multimodal knowledge sharing. A robotic FDR case study shows substantial improvements in energy efficiency (up to 99%) and task success (up to 72%) over legacy architectures, underscoring GoAgentNet's potential to enable scalable, sustainable 6G systems aligned with SDGs.

Abstract

6G services are evolving toward goal-oriented and AI-native communication, which are expected to deliver transformative societal benefits across various industries and promote energy sustainability. Yet today's networking architectures, built on complete decoupling of the applications and the network, cannot expose or exploit high-level goals, limiting their ability to adapt intelligently to service needs. This work introduces Goal-Oriented Multi-Agent Semantic Networking (GoAgentNet), a new architecture that elevates communication from data exchange to goal fulfilment. GoAgentNet enables applications and the network to collaborate by abstracting their functions into multiple collaborative agents, and jointly orchestrates multi-agent sensing, networking, computation, and control through semantic computation and cross-layer semantic networking, allowing the entire architecture to pursue unified application goals. We first outline the limitations of legacy network designs in supporting 6G services, based on which we highlight key enablers of our GoAgentNet design. Then, through three representative 6G usage scenarios, we demonstrate how GoAgentNet can unlock more efficient and intelligent services. We further identify unique challenges faced by GoAgentNet deployment and corresponding potential solutions. A case study on robotic fault detection and recovery shows that our GoAgentNet architecture improves energy efficiency by up to 99% and increases the task success rate by up to 72%, compared with the existing networking architectures without GoAgentNet, which underscores its potential to support scalable and sustainable 6G systems.

Figures (4)

• Figure 1: GoAgentNet architecture and key enablers.
• Figure 2: Examples of intent translation and knowledge graph in our GoAgentNet architecture.
• Figure 3: Robotic simulations and corresponding semantic representations.
• Figure 4: Comparison of consumed energy and task success rate between legacy and our proposed GoAgentNet networking architectures.