Leveraging Large Language Models for Auto-remediation in Microservices Architecture
Bibliographic record
Abstract
Microservices architecture is popular due to its scalability and flexibility. However, managing and troubleshooting distributed microservices-based systems can be challenging and time consuming. Auto-remediation of anomalies, that is the automated detection and root-causes generation and execution of repair scripts, can reduce the down-times and increase the availability of systems. This thesis will explore the potential and effectiveness of using large language models (LLMs) in auto-remediation. It will develop an auto-remediation framework to mitigate the effects of performance-based anomalies in self-adaptive microservice architectures. Multiple sample microservice applications as test-bed will be rigorously studied, and a dataset will be created to evaluate LLM-based codegeneration models using semantic, lexical, and correctness metrics in zero-shot and few-shot scenarios. Additionally, we will develop reliable prompts for automated Ansible runbook generation and assess their efficiency for orchestrating the auto-remediation process, including deployment, configuration changes, and system recovery to improve application reliability and operational efficiency.
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 | 0.002 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".