An LLM-driven dual-loop controller claims 72.5% stable-phase improvement over default and 153.3% over the strongest non-LLM baseline, but the comparison protocol inflates the gaps by scoring baselines during continued exploration.
Herding llamas: Using llms as an os module
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.OS 1years
2026 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
TuxBot: Semantic-Aware Online OS Tuning with Large Language Models
An LLM-driven dual-loop controller claims 72.5% stable-phase improvement over default and 153.3% over the strongest non-LLM baseline, but the comparison protocol inflates the gaps by scoring baselines during continued exploration.