Scaling Test-Driven Code Generation from Functions to Classes: An Empirical Study

• URL: http://arxiv.org/abs/2602.03557v1
• Date: Tue, 03 Feb 2026 14:04:05 GMT
• Title: Scaling Test-Driven Code Generation from Functions to Classes: An Empirical Study
• Authors: Yunhao Liang, Ruixuan Ying, Shiwen Ni, Zhe Cui,
• Abstract summary: Test-driven development (TDD) has been adopted to improve Large Language Model (LLM)-based code generation.<n>We scale test-driven code generation from functions to classes via an iterative TDD framework.<n>Our framework consistently improves class-level correctness by 12 to 26 absolute points and achieves up to 71% fully correct classes.
• Score: 15.939308390535722
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Test-driven development (TDD) has been adopted to improve Large Language Model (LLM)-based code generation by using tests as executable specifications. However, existing TDD-style code generation studies are largely limited to function-level tasks, leaving class-level synthesis where multiple methods interact through shared state and call dependencies underexplored. In this paper, we scale test-driven code generation from functions to classes via an iterative TDD framework. Our approach first analyzes intra-class method dependencies to derive a feasible generation schedule, and then incrementally implements each method under method-level public tests with reflection-style execution feedback and bounded repair iterations. To support test-driven generation and rigorous class-level evaluation, we construct ClassEval-TDD, a cleaned and standardized variant of ClassEval with consistent specifications, deterministic test environments, and complete method-level public tests. We conduct an empirical study across eight LLMs and compare against the strongest direct-generation baseline (the best of holistic, incremental, and compositional strategies). Our class-level TDD framework consistently improves class-level correctness by 12 to 26 absolute points and achieves up to 71% fully correct classes, while requiring only a small number of repairs on average. These results demonstrate that test-driven generation can effectively scale beyond isolated functions and substantially improve class-level code generation reliability. All code and data are available at https://anonymous.4open.science/r/ClassEval-TDD-C4C9/

Related papers

• LLMs for Automated Unit Test Generation and Assessment in Java: The AgoneTest Framework [2.501198441875755]
  AgoneTest is an evaluation framework for Large Language Model-generated unit tests in Java.<n>For the subset of tests that compile, LLM-generated tests can match or exceed human-written tests in terms of coverage and defect detection.
  arXiv  Detail & Related papers  (2025-11-25T15:33:00Z)
• Alignment with Fill-In-the-Middle for Enhancing Code Generation [56.791415642365415]
  We propose a novel approach that splits code snippets into smaller, granular blocks, creating more diverse DPO pairs from the same test cases.<n>Our approach demonstrates significant improvements in code generation tasks, as validated by experiments on benchmark datasets such as HumanEval (+), MBPP (+), APPS, LiveCodeBench, and BigCodeBench.
  arXiv  Detail & Related papers  (2025-08-27T03:15:53Z)
• UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance [65.01483640267885]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge.<n>We introduce UnitCoder, a systematic pipeline leveraging model-generated unit tests to guide and validate the code generation process.<n>Our work presents a scalable approach that leverages model-generated unit tests to guide the synthesis of high-quality code data from pre-training corpora.
  arXiv  Detail & Related papers  (2025-02-17T05:37:02Z)
• GenX: Mastering Code and Test Generation with Execution Feedback [7.225594526057816]
  We propose a novel approach that concurrently trains a code generation model and a test generation model.<n>We introduce two strategies for test and code data augmentation and a new scoring function for code and test ranking.<n>The results demonstrate that our models, when iteratively trained with an increasing number of test cases and code solutions, outperform those trained on the original dataset.
  arXiv  Detail & Related papers  (2024-12-18T03:18:21Z)
• Adapting Vision-Language Models to Open Classes via Test-Time Prompt Tuning [50.26965628047682]
  Adapting pre-trained models to open classes is a challenging problem in machine learning. In this paper, we consider combining the advantages of both and come up with a test-time prompt tuning approach. Our proposed method outperforms all comparison methods on average considering both base and new classes.
  arXiv  Detail & Related papers  (2024-08-29T12:34:01Z)
• Test-Driven Development for Code Generation [0.850206009406913]
  Large Language Models (LLMs) have demonstrated significant capabilities in generating code snippets directly from problem statements. This paper investigates if and how Test-Driven Development (TDD) can be incorporated into AI-assisted code-generation processes.
  arXiv  Detail & Related papers  (2024-02-21T04:10:12Z)
• PyTester: Deep Reinforcement Learning for Text-to-Testcase Generation [20.441921569948562]
  Test-driven development (TDD) mandates writing test cases based on requirements before writing the actual code. While writing test cases is the centerpiece of TDD, it is time-consuming, expensive, and often shunned by developers. We introduce PyTester, a Text-to-Testcase generation approach that can automatically generate correct, executable, complete, and effective test cases.
  arXiv  Detail & Related papers  (2024-01-15T10:21:58Z)
• Learning Deep Semantics for Test Completion [46.842174440120196]
  We formalize the novel task of test completion to automatically complete the next statement in a test method based on the context of prior statements and the code under test. We develop TeCo -- a deep learning model using code semantics for test completion.
  arXiv  Detail & Related papers  (2023-02-20T18:53:56Z)
• CodeExp: Explanatory Code Document Generation [94.43677536210465]
  Existing code-to-text generation models produce only high-level summaries of code. We conduct a human study to identify the criteria for high-quality explanatory docstring for code. We present a multi-stage fine-tuning strategy and baseline models for the task.
  arXiv  Detail & Related papers  (2022-11-25T18:05:44Z)
• Provably Consistent Partial-Label Learning [120.4734093544867]
  Partial-label learning (PLL) is a multi-class classification problem, where each training example is associated with a set of candidate labels. In this paper, we propose the first generation model of candidate label sets, and develop two novel methods that are guaranteed to be consistent. Experiments on benchmark and real-world datasets validate the effectiveness of the proposed generation model and two methods.
  arXiv  Detail & Related papers  (2020-07-17T12:19:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.