Synthetic Code Augmentation Effects on HumanEval Pass@1 Across Model Scales

This report synthesises findings from 12 peer-reviewed papers addressing the following research question: Does applying synthetic code augmentation during pre-training improve the pass@1 scores of code generation models on the HumanEval benchmark across different model scales. Abstract The rapid evolution of large language models (LLMs) has driven a transformative shift in artificial intelligence (AI), reshaping both research paradigms and practical applications. Distinguished from their predecessors by unprecedented scale and advanced capabilities. 9 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: Does applying synthetic code augmentation during pre-training improve the pass@1 scores of code generation models on the HumanEval benchmark across different model scales?

Autonomous literature synthesis. Automated review score: 8.2/10. Full text and citation available at Assignee Research.