KPI Assurance and LLMs for Intent-Based Management
Bibliographic record
Abstract
Intent-Based Management provides a shift in network management by automating the alignment of network operations with business objectives. However, primary challenges include: 1) intent processing (translate, decompose and identify the logic to fulfill the intent), and 2) ensuring intent conformance (ongoing adaptation of the logic to ensure the intent is met, considering dynamic conditions). We use a 3-tier Large Language Model (LLM) pipeline to convert intents into Policy Trees, that are then executed using closed control loop automation. In this paper, we focus on assurance that is tasked with continuous monitoring, verification, and validation of the operational state, and corrective actions to ensure conformance with the target objectives. To do so, we use a generic LLM (OpenAI's GPT) with in-context learning and well-established decision-making algorithms (feedback controllers) to determine assurance actions and remediate intent deviation. We show that AI-driven policies can support intent fulfillment and assurance, and we discuss current limitations, benefits, and future directions to address critical challenges in using AI for network management, towards improved generalizability, scalability, and overall trustworthiness.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.038 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.004 | 0.006 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.004 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".