SANNet: A Semantic-Aware Agentic AI Networking Framework for Multi-Agent Cross-Layer Coordination

2025-05-25

AI Summary

To address key challenges in Agentic AI networks (AgentNets)—including difficult goal discovery, weak multi-agent coordination, and frequent objective conflicts—this paper proposes a semantic-aware AI agent network framework. The framework enables automatic user-intent parsing and cross-layer (physical, protocol, and application) agent coordination, supporting fully autonomous network self-configuration, self-optimization, and self-adaptation. It introduces, for the first time, a dynamically weighted conflict-resolution mechanism that theoretically guarantees multi-agent objective consistency and generalizability, and achieves end-to-end semantic-driven task allocation. The framework integrates large language models (LLMs), multi-agent reinforcement learning (MARL), and an O-RAN/5G hardware prototype platform. Experimental results demonstrate a 42% improvement in task completion rate, a 37% reduction in end-to-end latency, and a 29% increase in resource utilization.

Technology Category

• Multiagent Systems: Agent/AI Theories and Architectures
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Search and Optimization: Algorithm Configuration

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Agentic AI networking (AgentNet) is a novel AI-native networking paradigm that relies on a large number of specialized AI agents to collaborate and coordinate for autonomous decision-making, dynamic environmental adaptation, and complex goal achievement. It has the potential to facilitate real-time network management alongside capabilities for self-configuration, self-optimization, and self-adaptation across diverse and complex networking environments, laying the foundation for fully autonomous networking systems in the future. Despite its promise, AgentNet is still in the early stage of development, and there still lacks an effective networking framework to support automatic goal discovery and multi-agent self-orchestration and task assignment. This paper proposes SANNet, a novel semantic-aware agentic AI networking architecture that can infer the semantic goal of the user and automatically assign agents associated with different layers of a mobile system to fulfill the inferred goal. Motivated by the fact that one of the major challenges in AgentNet is that different agents may have different and even conflicting objectives when collaborating for certain goals, we introduce a dynamic weighting-based conflict-resolving mechanism to address this issue. We prove that SANNet can provide theoretical guarantee in both conflict-resolving and model generalization performance for multi-agent collaboration in dynamic environment. We develop a hardware prototype of SANNet based on the open RAN and 5GS core platform. Our experimental results show that SANNet can significantly improve the performance of multi-agent networking systems, even when agents with conflicting objectives are selected to collaborate for the same goal.

Problem

• Lacks framework for automatic goal discovery in AgentNet
• Addresses conflicting objectives among collaborating AI agents
• Improves multi-agent coordination in dynamic networking environments

Innovation

• Semantic-aware AI networking for goal inference
• Dynamic weighting-based conflict-resolving mechanism
• Hardware prototype on open RAN and 5GS