ZEBRA reduces multi-phase budget allocation for LLM orchestration to a nonlinear knapsack problem solved via LLM-estimated utility curves and water-filling Lagrange search, recovering 94.4% of unconstrained quality at half budget versus 88.1% for direct LLM allocation on APPS coding tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration
ZEBRA reduces multi-phase budget allocation for LLM orchestration to a nonlinear knapsack problem solved via LLM-estimated utility curves and water-filling Lagrange search, recovering 94.4% of unconstrained quality at half budget versus 88.1% for direct LLM allocation on APPS coding tasks.