SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networking

2026-05-07

AI Summary

This work addresses the limitations of traditional network architectures, which struggle to support large-scale, semantics-aware multi-agent collaboration due to the separation of communication and computation. To overcome this, the paper proposes an emergent communication framework tailored for semantic-aware agent networks, enabling resource-constrained agents to autonomously evolve efficient communication protocols under bandwidth constraints by automatically interpreting user semantic intent and allocating subtasks accordingly. The core innovations include a bandwidth-adaptive importance filtering mechanism and a complexity regularizer grounded in the Minimum Description Length (MDL) principle, jointly optimizing the prioritized transmission of high-utility information and the generation of computation-efficient signals. Evaluated on the AgentNet prototype system, the proposed approach significantly outperforms existing methods, achieving higher task accuracy while substantially reducing both bandwidth consumption and computational overhead.

Abstract

Future networking systems are envisioned to become part of an agentic AI-native ecosystem in which a vast number of heterogeneous and specialized AI agents cooperate seamlessly to fulfill complex user requirements in real time. However, traditional networking paradigms are characterized by a rigid decoupling of communication and computation, which often leads to significant inefficiencies in large-scale agentic AI networking (AgentNet) systems. Emergent communication offers a novel solution by enabling autonomous agents that support task-specific signaling protocols for information exchange and collaborative coordination. In this paper, we consider a multi-agent emergent communication framework, tailored for semantic-aware AgentNet systems in which the user's semantic intent can be automatically detected, inferred, and linked to a set of sub-tasks to be assigned to a set of agents. We investigate how communication and signaling protocols can emerge among collaborative agents with computationally bounded intelligence under stringent bandwidth constraints. Our proposed framework, called SANEmerg, is designed to facilitate the emergence of communication for collaborative task fulfillment while adhering to the physical limits of AgentNet. SANEmerg incorporates a bandwidth-adaptable importance-filter that dynamically prioritizes the transmission of higher-contribution message dimensions, ensuring robust performance in bandwidth-limited environments. Furthermore, SANEmerg integrates a complexity-regularizer grounded in the Minimum Description Length (MDL) principle to facilitate the emergence of computationally bounded signaling. Evaluated via an AgentNet prototype and extensive experimentation, SANEmerg demonstrates significant performance improvements over state-of-the-art solutions, achieving superior task accuracy while significantly reducing bandwidth and computational overhead.

Problem

• Emergent Communication
• Semantic-aware Networking
• Agentic AI
• Bandwidth Constraints
• Multi-agent Collaboration

Innovation

• emergent communication
• semantic-aware networking
• agentic AI
• bandwidth-adaptable filtering
• Minimum Description Length