AI RESEARCH
Inference-Time Code Selection via Symbolic Equivalence Partitioning
arXiv CS.LG
•
ArXi:2604.06485v1 Announce Type: new "Best-of-N" selection is a popular inference-time scaling method for code generation using Large Language Models (LLMs). However, to reliably identify correct solutions, existing methods often depend on expensive or stochastic external verifiers. In this paper, we propose Symbolic Equivalence Partitioning, a selection framework that uses symbolic execution to group candidate programs by semantic behavior and select a representative from the dominant functional partition.