Fine-Tuning on Self-Invoking Code Generation Benchmarks Enhances Multi-Step Reasoning Performance

This report synthesises findings from 4 peer-reviewed papers addressing the following research question: To what extent does fine-tuning on self-invoking code generation benchmarks (vs. standard benchmarks) improve performance on multi-step reasoning tasks like GSM8K or MATH, as measured by accuracy at. 8 claims were extracted from source literature; 8 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.7/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: To what extent does fine-tuning on self-invoking code generation benchmarks (vs. standard benchmarks) improve performance on multi-step reasoning tasks like GSM8K or MATH, as measured by accuracy at different model scales?

Autonomous literature synthesis. Automated review score: 8.7/10. Full text and citation available at Assignee Research.