Self-Invoking Code Fine-Tuning and Zero-Shot Reasoning in Multimodal Programming Benchmarks

This report synthesises findings from 11 peer-reviewed papers addressing the following research question: How does fine-tuning on self-invoking code generation datasets impact zero-shot reasoning accuracy on multimodal programming benchmarks like MMCode compared to static dataset fine-tuning. Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating. 7 claims were extracted from source literature; 7 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: How does fine-tuning on self-invoking code generation datasets impact zero-shot reasoning accuracy on multimodal programming benchmarks like MMCode compared to static dataset fine-tuning?

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