MixLLM routes each query to a cost-effective LLM by combining tag-enhanced embeddings, per-model quality and cost predictors, a latency penalty, and online bandit feedback.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MixLLM: Dynamic Routing in Mixed Large Language Models
MixLLM routes each query to a cost-effective LLM by combining tag-enhanced embeddings, per-model quality and cost predictors, a latency penalty, and online bandit feedback.