Large language models (LLMs) are increasingly being used in network operations (NetOps) and artificial intelligence for IT operations (AIOps) for tasks ranging from telemetry retrieval and incident diagnosis to configuration planning and bounded remediation. As these systems acquire greater access to operational tools, a central question is whether operational assurance develops commensurately with the authority granted to them. This survey examines that question through a structured, evidence-stratified review of agentic NetOps and AIOps, spanning directly evaluated LLM systems, operational mechanisms, transferred evidence, and normative guidance. We organise the field around autonomy, tool scope, evidence traces, assurance controls, evaluation, security, and governance, and introduce an operational assurance contract that links each autonomy level to permitted tools, required evidence, independent gates, execution budgets, rollout and rollback duties, and audit requirements. The synthesis indicates a capability–assurance gap: evidence is comparatively strong for read-oriented assistance and tool-grounded diagnosis, but becomes substantially less complete as systems approach configuration change, bounded execution, and closed-loop operation. We therefore develop a workflow-level evaluation framework covering evidence quality, tool use, policy and invariant compliance, staged execution, recovery, calibration, cost, and human intervention, together with a threat model for prompt-borne attacks, compromised operational evidence, excessive agency, privilege boundaries, and auditability. The resulting view treats agentic NetOps and AIOps as constrained operational control, in which increasing autonomy requires correspondingly stronger evidence, independently enforced safeguards, and recovery mechanisms.
Various nonparametric estimators for modelling the transition probabilities in multi-state models have been proposed, e.g., the Aalen-Johansen estimator, the landmark Aalen-Johansen estimator, and a hybrid Aalen-Johansen estimator. While the Aalen-Johansen estimator is generally only consistent under the rather restrictive Markov assumption, the landmark Aalen-Johansen estimator can handle non-Markov multi-state models. However, the landmark Aalen-Johansen estimator leads to a strict data reduction and, thus, to an increased variance. The hybrid Aalen-Johansen estimator serves as a compromise by, firstly, checking with a log-rank-based test whether the Markov assumption is satisfied. Secondly, landmarking is only applied if the Markov assumption is rejected. A new hybrid Aalen-Johansen estimator is proposed which uses a Cox model instead of the log-rank-based test to check the Markov assumption in the first step. Furthermore, the four estimators are compared in an extensive simulation study across Markov, semi-Markov, and distinct non-Markov settings. In order to get deep insights into the performance of the estimators, four different measures are considered: bias, variance, root mean squared error, and coverage rate. The main result of the simulation study is that the hybrid Aalen-Johansen estimators yield favourable results across various measures and settings.
Abstract Owing to the drastic environmental change and frequently occurring disasters like bushfires in Australia and New South Wales (NSW) in particular, this research study aims to develop an unmanned aerial vehicles (UAVs) assisted bushfire detection and prevention system. A rule-based verification framework is developed to identify critical infrastructure impacted by bushfires using a metaheuristic optimization algorithm, with reliance on real-time data. Moreover, the affected area coverage of UAVs is maximized by considering limited resources and energy constraints for better precision of results. Finally, a mathematical optimization model is developed and tested for path planning of different UAV populations in affected bushfire regions. Within the realm of competing techniques for UAVs path planning, this research study extensively scrutinized and assessed four distinct optimization algorithms, including whale optimization algorithm (WOA), grey wolf optimizer (GWO), and particle swarm optimization (PSO). Results indicated that our proposed model, efficient particle swarm optimization (EPSO), consistently outperforms other techniques across all cases. However, the degree of its superiority varies among different scenarios. In Case 3, EPSO exhibits the most dominance, presenting notable improvements with approximately 18.35% to 54.47% reductions in cost and time compared with WOA, GWO, and PSO.
This paper makes the argument for treating the response of small catchments as an exercise in the identification of hysteretic functions as a way of overcoming the impossibility of knowing all the small-scale detail of time variable and spatial heterogeneous catchment processes. An initial form of analysis is proposed based on the Data-Based Mechanistic (DBM) transfer function methodology to define functions for classes of events based on rainfall input volumes and antecedent flow as an index of catchment wetness. From the resulting transfer functions, event-scale storage-discharge plots can be derived if within-event evapotranspiration is neglected as small relative to event inputs. The great hysteresis challenge is to find a way of identifying a more continuous mechanistic function that allows for the change in input-output gains and transfer function state variables directly from the observed data without invoking a particular conceptual storage model structure (or structures) or a difficult-to-interpret machine-learning framework.
