Design of a multi-agent system for autonomous database administration
Bibliographic record
Abstract
As more and more businesses and services find themselves online due to the Internet phenomenon, a plethora of information sources is now available. These trends have rendered databases an indispensable component of daily life and have increased their complexity significantly, which has, in turn, amplified the workload on database administrators (DBAs). This has given rise to an increasing need for self-managing and self-administering databases. We present the analysis and design of a novel and innovative solution to address the problem of overburdened and expensive DBAs. We propose a self-administering wrapper around database systems in the form of an intelligent multi-agent system tool that autonomously and rationally administers and maintains relational databases. A planned implementation of the agent-based system which proactively or reactively identifies and resolves a small sub-set of DBA tasks is discussed and the Gaia methodology is used to outline the detailed analysis and design of the same using role models and interaction models. A brief description of the functionalities, responsibilities and components of each agent in the planned multi-agent system is presented.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".