We investigate Functional Majority Voting (FMV), a method based on functional consensus for code generation with Large Language Models, which identifies a representative solution from multiple generations using their runtime execution signatures on test inputs. We find that FMV is an effective test-time inference strategy, substantially boosting performance on LiveCodeBench without a large compute overhead. Furthermore, we extend the utility of functional consensus and apply it as an aggregation strategy for label-free Test-Time Reinforcement Learning. We demonstrate that this increases pass@1 on holdout tasks, but find no evidence of self-improvement beyond the base model's performance ceiling.
@article{arxiv.2604.15618,
title = {Majority Voting for Code Generation},
author = {Tim Launer and Jonas Hübotter and Marco Bagatella and Ido Hakimi and Andreas Krause},
journal= {arXiv preprint arXiv:2604.15618},
year = {2026}
}