Multimodal vs. Text-Only Llama-2 Performance in Self-Invoking Code Generation

This report synthesises findings from 14 peer-reviewed papers addressing the following research question: How does the performance of multimodal Llama-2 models in self-invoking code generation tasks compare to text-only versions when evaluated on HumanEval Pro and MBPP Pro, using pass@1 and pass@k. 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. 10 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the performance of multimodal Llama-2 models in self-invoking code generation tasks compare to text-only versions when evaluated on HumanEval Pro and MBPP Pro, using pass@1 and pass@k metrics under constrained inference budgets?

Autonomous literature synthesis. Automated review score: 8.0/10. Full text and citation available at Assignee Research.