Understanding Specification-Driven Code Generation with LLMs: An Empirical Study Design

TL;DR

This paper proposes an empirical study design using a Visual Studio Code extension to analyze how human-guided specification and testing influence LLM-assisted code generation quality and efficiency.

Contribution

It introduces CURRANTE, a tool for structured, human-in-the-loop LLM code generation, enabling detailed analysis of developer interactions and model performance.

Findings

Insights into human intervention effects on code quality

Data on efficiency metrics like time-to-pass

Analysis of iteration behaviors in code generation

Abstract

Large Language Models (LLMs) are increasingly integrated into software development workflows, yet their behavior in structured, specification-driven processes remains poorly understood. This paper presents an empirical study design using CURRANTE, a Visual Studio Code extension that enables a human-in-the-loop workflow for LLM-assisted code generation. The tool guides developers through three sequential stages--Specification, Tests, and Function--allowing them to define requirements, generate and refine test suites, and produce functions that satisfy those tests. Participants will solve medium-difficulty problems from the LiveCodeBench dataset, while the tool records fine-grained interaction logs, effectiveness metrics (e.g., pass rate, all-pass completion), efficiency indicators (e.g., time-to-pass), and iteration behaviors. The study aims to analyze how human intervention in specification and test refinement influences the quality and dynamics of LLM-generated code. The results will provide empirical insights into the design of next-generation development environments that align human reasoning with model-driven code generation.