Research
Majority Voting for Code Generation
arXiv:2604.15618v1 Announce Type: new Abstract: We investigate Functional Majority Voting (FMV), a method based on functional consensus for code generation with Large Language Models, which identifies
arXiv:2604.15618v1 Announce Type: new Abstract: 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.
Related
- C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functions
- HYPERHEURIST: A Simulated Annealing-Based Control Framework for LLM-Driven Code Generation in Optimized Hardware Design
- MedVerse: Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution
- Quantifying and Understanding Uncertainty in Large Reasoning Models
Source: arXiv cs.LG | 2026-04-20