Symbiotic Agents: A Novel Paradigm for Trustworthy AGI-driven Networks

TL;DR

This paper introduces symbiotic agents combining LLMs with real-time optimization for trustworthy AGI-driven networks, demonstrating significant improvements in decision accuracy, resource efficiency, and adaptability in 5G testbeds.

Contribution

It proposes a novel symbiotic agent paradigm integrating LLMs with optimizers, and designs two agent types for network management and SLA negotiation, advancing the development of trustworthy AGI networks.

Findings

Symbiotic agents reduce decision errors fivefold compared to standalone LLMs.

Smaller language models achieve similar accuracy with 99.9% less GPU resource use.

RAN over-utilization is reduced by approximately 44%.

Abstract

Large Language Model (LLM)-based autonomous agents are expected to play a vital role in the evolution of 6G networks, by empowering real-time decision-making related to management and service provisioning to end-users. This shift facilitates the transition from a specialized intelligence approach, where artificial intelligence (AI) algorithms handle isolated tasks, to artificial general intelligence (AGI)-driven networks, where agents possess broader reasoning capabilities and can manage diverse network functions. In this paper, we introduce a novel agentic paradigm that combines LLMs with real-time optimization algorithms towards Trustworthy AI, defined as symbiotic agents. Optimizers at the LLM's input-level provide bounded uncertainty steering for numerically precise tasks, whereas output-level optimizers supervised by the LLM enable adaptive real-time control. We design and implement two novel agent types including: (i) Radio Access Network optimizers, and (ii) multi-agent negotiators for Service-Level Agreements (SLAs). We further propose an end-to-end architecture for AGI networks and evaluate it on a 5G testbed capturing channel fluctuations from moving vehicles. Results show that symbiotic agents reduce decision errors fivefold compared to standalone LLM-based agents, while smaller language models (SLM) achieve similar accuracy with a 99.9% reduction in GPU resource overhead and in near-real-time loops of 82 ms. A multi-agent demonstration for collaborative RAN on the real-world testbed highlights significant flexibility in service-level agreement and resource allocation, reducing RAN over-utilization by approximately 44%. Drawing on our findings and open-source implementations, we introduce the symbiotic paradigm as the foundation for next-generation, AGI-driven networks-systems designed to remain adaptable, efficient, and trustworthy even as LLMs advance.