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

Abstract

Abstract: This report synthesises findings from 13 peer-reviewed papers addressing the following research question: How do multimodal LLMs perform on self-invoking code generation tasks (HumanEval Pro) compared to text-only models when evaluated on problems requiring multi-step reasoning, measured by exact match. We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented with a base problem and a related, more complex problem. 4 claims were extracted from source literature; 3 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 7.6/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How do multimodal LLMs perform on self-invoking code generation tasks (HumanEval Pro) compared to text-only models when evaluated on problems requiring multi-step reasoning, measured by exact match accuracy and solution correctness rates?

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