An online multi-armed bandit that selects among symbolic solvers and LLM-prompt combinations for program synthesis solves 37.2% more queries than the best single solver and reaches 96% of the virtual best solver's performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Online Prompt Selection for Program Synthesis
An online multi-armed bandit that selects among symbolic solvers and LLM-prompt combinations for program synthesis solves 37.2% more queries than the best single solver and reaches 96% of the virtual best solver's performance.