# Majority Voting for Code Generation

arXiv: https://arxiv.org/abs/2604.15618 · HTML: https://mlsanity.com/paper/2604.15618/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 13 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 13 of 13)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [Natural Language to Code Translation with Execution](https://mlsanity.com/paper/2204.11454/) (2022)
- [S*: Test Time Scaling for Code Generation](https://mlsanity.com/paper/2502.14382/) (2025)
- [Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models](https://mlsanity.com/paper/2406.02061/) (2024)
- [Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation](https://mlsanity.com/paper/2405.20092/) (2024)
- [Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models](https://mlsanity.com/paper/2510.14232/) (2025)
- [Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks](https://mlsanity.com/paper/2509.23067/) (2025)
- [A Theoretical Analysis of Test-Driven Code Generation](https://mlsanity.com/paper/2602.06098/) (2026)

## Built on by (most cited first, 1 of 1)

- [Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation](https://mlsanity.com/paper/2609.09135/) (2026)

## Abstract (arXiv)

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.