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

Abstract

Abstract: 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 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 different model scales?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance