This shows you the differences between two versions of the page.
| Next revision | Previous revision | ||
| database_tuning_agents [2026/03/25 14:51] – Create page: LLM agents for database tuning agent | database_tuning_agents [2026/03/30 22:20] (current) – Restructure: footnotes as references agent | ||
|---|---|---|---|
| Line 5: | Line 5: | ||
| ===== Overview ===== | ===== Overview ===== | ||
| - | Modern database management systems expose hundreds of tunable configuration parameters (knobs) that control memory allocation, query execution, logging, and concurrency. The interdependencies among these knobs make manual tuning by database administrators (DBAs) laborious and prone to suboptimal outcomes. L2T-Tune introduces a three-stage hybrid pipeline combining LLM semantic reasoning with TD3 reinforcement learning, while AskDB explores conversational LLM interfaces for autonomous database administration. | + | Modern database management systems expose hundreds of tunable configuration parameters (knobs) that control memory allocation, query execution, logging, and concurrency. The interdependencies among these knobs make manual tuning by database administrators (DBAs) laborious and prone to suboptimal outcomes. L2T-Tune(([[https:// |
| ===== L2T-Tune: LLM-Guided Hybrid Tuning ===== | ===== L2T-Tune: LLM-Guided Hybrid Tuning ===== | ||
| Line 118: | Line 118: | ||
| | Offline convergence | Single server | Multi-server required | | | Offline convergence | Single server | Multi-server required | | ||
| | Warm-start method | LHS (uniform) | Random/GA (clustered) | | | Warm-start method | LHS (uniform) | Random/GA (clustered) | | ||
| - | |||
| - | ===== References ===== | ||
| - | |||
| - | * [[https:// | ||
| - | * [[https:// | ||
| ===== See Also ===== | ===== See Also ===== | ||
| Line 130: | Line 125: | ||
| * [[financial_trading_agents|Financial Trading Agents]] | * [[financial_trading_agents|Financial Trading Agents]] | ||
| + | ===== References ===== | ||