Semantic Voting: Execution-Grounded Consensus for LLM Code Generation

arXiv:2605.08680v1 Announce Type: cross Abstract: LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix textual voting, ranking, and execution-based agreement, but the relative contribution of each component remains unclear. We study 18 configurations across different models, thinking levels, and benchmarks, comparing output-pattern majority voting, weighted voting, MBR-Exec, and SemanticVote - a met