Code Health in LLM-Based Test Generation: Effectiveness and Token Efficiency

• URL: http://arxiv.org/abs/2608.18645v1
• Date: Wed, 19 Aug 2026 07:47:43 GMT
• Title: Code Health in LLM-Based Test Generation: Effectiveness and Token Efficiency
• Abstract summary: Coding agents powered by Large Language Models (LLMs) are now prominent in software engineering.<n>Previous work has shown that AI tools perform better on high-quality source code that is easy to maintain.<n>We investigate how the effectiveness of LLM-generated unit tests varies across maintainability levels measured by CodeScene's CodeHealth.
• Score: 4.507833066754929
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Coding agents powered by Large Language Models (LLMs) are now prominent in software engineering. Previous work has shown that AI tools perform better on high-quality source code that is easy to maintain. In this study, we investigate how the effectiveness of LLM-generated unit tests varies across maintainability levels measured by CodeScene's CodeHealth (CH). We assess test effectiveness using traditional coverage metrics and mutation score across Python, Java, and C++. Moreover, we study how code with different levels of CH translates into input tokens using common industrial tokenizers. Our results suggest that CH provides a weak but consistent signal of LLM-generated test effectiveness and is negatively correlated with input-token count. These findings provide further evidence for a relationship between maintainability and LLM-based software development.

Related papers

• Protocode: Prototype-Driven Interpretability for Code Generation in LLMs [5.8296917468117835]
  Large Language Models (LLMs) have been widely adopted for various tasks such as text summarization, question answering, speech-to-text translation, and more.<n>Our work focuses on automatically sampling In-Context Learning (ICL) demonstrations which can improve model performance and enhance the interpretability of the generated code.
  arXiv  Detail & Related papers  (2025-09-27T00:32:45Z)
• Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
  Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
  arXiv  Detail & Related papers  (2025-05-28T17:57:47Z)
• Is Compression Really Linear with Code Intelligence? [60.123628177110206]
  textitFormat Annealing is a lightweight, transparent training methodology designed to assess the intrinsic capabilities of pre-trained models equitably.<n>Our empirical results reveal a fundamental logarithmic relationship between measured code intelligence and bits-per-character (BPC)<n>Our work provides a more nuanced understanding of compression's role in developing code intelligence and contributes a robust evaluation framework in the code domain.
  arXiv  Detail & Related papers  (2025-05-16T16:59:14Z)
• Improving the Readability of Automatically Generated Tests using Large Language Models [7.7149881834358345]
  We propose to combine the effectiveness of search-based generators with the readability of LLM generated tests.<n>Our approach focuses on improving test and variable names produced by search-based tools, while keeping their semantics unchanged.
  arXiv  Detail & Related papers  (2024-12-25T09:08:53Z)
• Examination of Code generated by Large Language Models [35.51378656555693]
  Large language models (LLMs) are transforming software development by automating code generation. To assess the current state of LLMs in generating correct code of high quality, we conducted controlled experiments with ChatGPT and Copilot. We observed significant differences between the LLMs, between the languages, between algorithm and test codes, and over time.
  arXiv  Detail & Related papers  (2024-08-29T15:12:16Z)
• Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph [83.90988015005934]
  Uncertainty quantification is a key element of machine learning applications.<n>We introduce a novel benchmark that implements a collection of state-of-the-art UQ baselines.<n>We conduct a large-scale empirical investigation of UQ and normalization techniques across eleven tasks, identifying the most effective approaches.
  arXiv  Detail & Related papers  (2024-06-21T20:06:31Z)
• Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting [78.48355455324688]
  We propose a novel zero-shot synthetic code detector based on the similarity between the original code and its LLM-rewritten variants.<n>Our results demonstrate a significant improvement over existing SOTA synthetic content detectors.
  arXiv  Detail & Related papers  (2024-05-25T08:57:28Z)
• Assured LLM-Based Software Engineering [51.003878077888686]
  This paper is an outline of the content of the keynote by Mark Harman at the International Workshop on Interpretability, Robustness, and Benchmarking in Neural Software Engineering, Monday 15th April 2024, Lisbon, Portugal.
  arXiv  Detail & Related papers  (2024-02-06T20:38:46Z)
• Testing LLMs on Code Generation with Varying Levels of Prompt Specificity [0.0]
  Large language models (LLMs) have demonstrated unparalleled prowess in mimicking human-like text generation and processing. The potential to transform natural language prompts into executable code promises a major shift in software development practices.
  arXiv  Detail & Related papers  (2023-11-10T23:41:41Z)
• Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITE [62.13435256279566]
  Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks. However, their large size makes their inference slow and computationally expensive. We show that it enables these layers to acquire 'good' generation ability without affecting the generation ability of the final layer.
  arXiv  Detail & Related papers  (2023-10-28T04:07:58Z)
• Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation [20.45045253933097]
  We propose EvalPlus -- a code synthesis evaluation framework to rigorously benchmark the functional correctness of LLM-synthesized code. EvalPlus augments a given evaluation dataset with large amounts of test-cases newly produced by an automatic test input generator. We show that HumanEval+ is able to catch significant amounts of previously undetected wrong code.
  arXiv  Detail & Related papers  (2023-05-02T05:46:48Z)
• LEVER: Learning to Verify Language-to-Code Generation with Execution [64.36459105535]
  We propose LEVER, a simple approach to improve language-to-code generation by learning to verify the generated programs with their execution results. Specifically, we train verifiers to determine whether a program sampled from the LLMs is correct or not based on the natural language input, the program itself and its execution results. LEVER consistently improves over the base code LLMs(4.6% to 10.9% with code-davinci) and achieves new state-of-the-art results on all of them.
  arXiv  Detail & Related papers  (2023-02-16T18:23:22Z)
• An Exploratory Study on Code Attention in BERT [8.488193857572211]
  We investigate the attention behavior of PLM on code and compare it with natural language. We show that BERT pays more attention to syntactic entities, specifically identifiers and separators, in contrast to the most attended token in NLP. The findings can benefit the research community by using code-specific representations instead of applying the common embeddings used in NLP.
  arXiv  Detail & Related papers  (2022-04-05T21:23:10Z)

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.