LLM routing is framed as a budget-constrained contextual bandit, solved by a preference-prior initialized LinUCB variant with an online multi-choice knapsack cost policy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptive LLM Routing under Budget Constraints
LLM routing is framed as a budget-constrained contextual bandit, solved by a preference-prior initialized LinUCB variant with an online multi-choice knapsack cost policy.