Communications-Incentivized Collaborative Reasoning in NetGPT through Agentic Reinforcement Learning

TL;DR

This paper introduces a unified NetGPT framework for next-generation wireless networks that enables autonomous reasoning and dynamic delegation to specialized agents, enhancing adaptability and collaboration in AI-native communication systems.

Contribution

It proposes a modular, agentic NetGPT architecture with reinforcement learning for collaborative reasoning, addressing the limitations of siloed AI deployments in communication networks.

Findings

NetGPT effectively balances internal reasoning and agent invocation.

The framework improves scalability and distributed intelligence.

Reinforcement learning enhances collaborative decision-making.

Abstract

The evolution of next-Generation (xG) wireless networks marks a paradigm shift from connectivity-centric architectures to Artificial Intelligence (AI)-native designs that tightly integrate data, computing, and communication. Yet existing AI deployments in communication systems remain largely siloed, offering isolated optimizations without intrinsic adaptability, dynamic task delegation, or multi-agent collaboration. In this work, we propose a unified agentic NetGPT framework for AI-native xG networks, wherein a NetGPT core can either perform autonomous reasoning or delegate sub-tasks to domain-specialized agents via agentic communication. The framework establishes clear modular responsibilities and interoperable workflows, enabling scalable, distributed intelligence across the network. To support continual refinement of collaborative reasoning strategies, the framework is further enhanced through Agentic reinforcement learning under partially observable conditions and stochastic external states. The training pipeline incorporates masked loss against external agent uncertainty, entropy-guided exploration, and multi-objective rewards that jointly capture task quality, coordination efficiency, and resource constraints. Through this process, NetGPT learns when and how to collaborate, effectively balancing internal reasoning with agent invocation. Overall, this work provides a foundational architecture and training methodology for self-evolving, AI-native xG networks capable of autonomous sensing, reasoning, and action in complex communication environments.