arXiv subjects

Fin Gentzen

Publications and source records attributed to Fin Gentzen.

5 recordsLinked to original sources

arXiv2026

A Self-Calibrating Agentic AI Framework for Autonomous Edge Resource Allocation

Large Language Models (LLMs) are increasingly deployed as autonomous agents, transitioning from static conversational interfaces to dynamic systems capable of complex reasoning, tool execution, and decision-making. However, the operational reliability of these agentic AI systems is fundamentally challenged by the absence of reliable ground truth in open-ended environments and the risk of increasing operational drift over time. To address this challenge, we propose and experimentally evaluate an agentic AI framework, designed to enforce autonomous integrity within LLM-driven systems. We design a self-calibration mechanism that mitigates drift and dynamically approximates ground truth by incorporating an ARIMA forecaster, without requiring continuous human oversight. To demonstrate the effectiveness and reliability of our methodology, we apply it to the complex domain of profiling the resource usage of zero-knowledge workloads in edge computing networks. Experimental results show that the proposed self-calibrating agentic framework successfully profiles the zero-knowledge workloads, achieving a higher accuracy than baseline LLM agents by 91.7% for resource usage prediction and improving the prediction speed by 71.7% compared to pure profiling, establishing a robust foundation for deploying autonomous AI in decentralized infrastructures. Furthermore, the ground truth generation using the proposed ARIMA leaping algorithm is 52% faster than a standard ARIMA forecasting algorithm, while achieving the same accuracy.

cs.NI↗

arXiv2026

Enhancing Secure Intent-Based Networking with an Agentic AI: The EU Project MARE Approach

In the EU project MARE, a novel plane was proposed and used in combination with intent-based networking (IBN), allowing the operator to focus on what, rather than on how. Recently, LLMs have been successfully employed to translate the high-level intents into low-level actions. The open challenge is to understand how IBN can be effectively enhanced with LLM and the emerging agentic AI for security purposes. Enhancing IBN with an agentic AI paradigm introduces significant challenges that existing solutions do not fully address. This paper proposes an enhanced IBN framework with a strong security focus toward agentic AI. We address the architectural and security requirements for a multi-agent intent-based system (IBS) architecture, including a multi-domain IBN. We propose a hierarchical multi-agent and multi-vendor architecture that can also be applied more broadly in 6G architectures and beyond, beyond the security architecture proposed in MARE. The architecture incorporates an interactive intent-processing pipeline using LLMs, and it also allows the IBS to connect to external security knowledge bases, such as MITRE ATT\&CK, MITRE FiGHT, and NIST.

cs.NI↗

arXiv2026

Efficient Self-Learning and Model Versioning for AI-native O-RAN Edge

The AI-native vision of 6G requires Radio Access Networks to train, deploy, and continuously refine thousands of machine learning (ML) models that drive real-time radio network optimization. Although the Open RAN (O-RAN) architecture provides open interfaces and an intelligent control plane, it leaves the life-cycle management of these models unspecified. Consequently, operators still rely on ad-hoc, manual update practices that can neither scale across the heterogeneous, multi-layer stack of Cell-Site, Edge-, Regional-, and Central-Cloud domains, nor across the three O-RAN control loops (real-, near-real-, and non-real-time). We present a self-learning framework that provides an efficient closed-loop version management for an AI-native O-RAN edge. In this framework, training pipelines in the Central/Regional Cloud continuously generate new models, which are cataloged along with their resource footprints, security scores, and accuracy metrics in a shared version repository. An Update Manager consults this repository and applies a self-learning policy to decide when and where each new model version should be promoted into operation. A container orchestrator then realizes these decisions across heterogeneous worker nodes, enabling multiple services (rApps, xApps, and dApps) to obtain improved inference with minimal disruption. Simulation results show that an efficient RL-driven decision-making can guarantee quality of service, bounded latencies while balancing model accuracy, system stability, and resilience.

cs.NI↗

arXiv2024

Effective ML Model Versioning in Edge Networks

Machine learning (ML) models, data and software need to be regularly updated whenever essential version updates are released and feasible for integration. This is a basic but most challenging requirement to satisfy in the edge, due to the various system constraints and the major impact that an update can have on robustness and stability. In this paper, we formulate for the first time the ML model versioning optimization problem, and propose effective solutions, including the update automation with reinforcement learning (RL) based algorithm. We study the edge network environment due to the known constraints in performance, response time, security, and reliability, which make updates especially challenging. The performance study shows that model version updates can be fully and effectively automated with reinforcement learning method. We show that for every range of server load values, the proper versioning can be found that improves security, reliability and/or ML model accuracy, while assuring a comparably lower response time.

cs.NI↗

arXiv2024

An experimental study of the response time in an edge-cloud continuum with ClusterLink

In this paper, we conduct an experimental study to provide a general sense of the application response time implications that inter-cluster communication experiences at the edge at the example of a specific IoT-edge-cloud contiuum solution from the EU Project ICOS called ClusterLink. We create an environment to emulate different networking topologies that include multiple cloud or edge sites scenarios, and conduct a set of tests to compare the application response times via ClusterLink to direct communications in relation to node distances and request/response payload size. Our results show that, in an edge context, ClusterLink does not introduce a significant processing overhead to the communication for small payloads as compared to cloud. For higher payloads and on comparably more aged consumer hardware, ClusterLink version 0.2 introduces communication overhead relative to the delay experienced on the link.

cs.NI↗