Testing with AI Agents: An Empirical Study of Test Generation Frequency, Quality, and Coverage

• URL: http://arxiv.org/abs/2603.13724v1
• Date: Sat, 14 Mar 2026 03:01:44 GMT
• Title: Testing with AI Agents: An Empirical Study of Test Generation Frequency, Quality, and Coverage
• Abstract summary: This study presents an empirical analysis of test generation by agent-based coding tools using the AIDev dataset.<n>We extracted 2,232 commits containing test-related changes and investigated three aspects: the frequency of test additions, the structural characteristics of the generated tests, and their impact on code coverage.<n>Our findings reveal that (i) AI authored 16.4% of all commits adding tests in real-world repositories, (ii) AI-generated test methods exhibit distinct structural patterns, featuring longer code and a higher density of assertions, and (iii) AI-generated tests contribute to code coverage comparable to human-written tests
• Score: 1.6782288954198918
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent-based coding tools have transformed software development practices. Unlike prompt-based approaches that require developers to manually integrate generated code, these agent-based tools autonomously interact with repositories to create, modify, and execute code, including test generation. While many developers have adopted agent-based coding tools, little is known about how these tools generate tests in real-world development scenarios or how AI-generated tests compare to human-written ones. This study presents an empirical analysis of test generation by agent-based coding tools using the AIDev dataset. We extracted 2,232 commits containing test-related changes and investigated three aspects: the frequency of test additions, the structural characteristics of the generated tests, and their impact on code coverage. Our findings reveal that (i) AI authored 16.4% of all commits adding tests in real-world repositories, (ii) AI-generated test methods exhibit distinct structural patterns, featuring longer code and a higher density of assertions while maintaining lower cyclomatic complexity through linear logic, and (iii) AI-generated tests contribute to code coverage comparable to human-written tests, frequently achieving positive coverage gains across several projects.

Related papers

• Multi-Agent LLM Collaboration for Unit Test Generation via Human-Testing-Inspired Workflows [18.32804849870551]
  Large Language Models (LLMs) have spurred a surge of research into automated unit test generation.<n>We propose TestAgent, an LLM-based test generation approach that emulates human testing practices via a multi-agent collaboration mechanism.<n>TestAgent achieves 97.46% execution rate, 92.34% line coverage, 90.24% branch coverage, and 83.69% mutation score on six Java projects.
  arXiv  Detail & Related papers  (2026-07-10T05:16:54Z)
• Sakura: An Approach for Generating Complex Tests from Natural Language Test Descriptions [46.562528718959506]
  Sakura is a framework for generating tests from natural language (NL) descriptions of developer intent.<n>Sakura decomposes NL descriptions into structured blocks and processes them using a multi-agent system.<n>Sakura significantly outperforms off-the-truth agentic tools such as Gemini CLI.
  arXiv  Detail & Related papers  (2026-05-30T04:49:10Z)
• Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation [47.85891728056131]
  PRDBench is a novel benchmark comprising 50 real-world Python projects across 20 domains, each with structured Product Requirement Document (PRD) requirements, comprehensive evaluation criteria, and reference implementations.<n>We employ an Agent-as-a-Judge paradigm to score agent outputs, enabling the evaluation of various test types beyond unit tests.
  arXiv  Detail & Related papers  (2025-10-28T12:26:45Z)
• Hamster: A Large-Scale Study and Characterization of Developer-Written Tests [44.65515600399573]
  We study developer-written tests for Java applications, covering 1.7 million test cases from open-source repositories.<n>Our results highlight that a vast majority of developer-written tests exhibit characteristics beyond the capabilities of current ATG tools.<n>We identify promising research directions that can help bridge the gap between current tool capabilities and more effective tool support for developer testing practices.
  arXiv  Detail & Related papers  (2025-09-30T13:08:23Z)
• From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking [48.90371827091671]
  AutoExperiment is a benchmark that evaluates AI agents' ability to implement and run machine learning experiments.<n>We evaluate state-of-the-art agents and find that performance degrades rapidly as $n$ increases.<n>Our findings highlight critical challenges in long-horizon code generation, context retrieval, and autonomous experiment execution.
  arXiv  Detail & Related papers  (2025-06-24T15:39:20Z)
• Commit0: Library Generation from Scratch [77.38414688148006]
  Commit0 is a benchmark that challenges AI agents to write libraries from scratch.<n>Agents are provided with a specification document outlining the library's API as well as a suite of interactive unit tests.<n> Commit0 also offers an interactive environment where models receive static analysis and execution feedback on the code they generate.
  arXiv  Detail & Related papers  (2024-12-02T18:11:30Z)
• Disrupting Test Development with AI Assistants [1.024113475677323]
  Generative AI-assisted coding tools like GitHub Copilot, ChatGPT, and Tabnine have significantly transformed software development. This paper analyzes how these innovations impact productivity and software test development metrics.
  arXiv  Detail & Related papers  (2024-11-04T17:52:40Z)
• Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
  We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
  arXiv  Detail & Related papers  (2024-10-02T09:11:10Z)
• ASTER: Natural and Multi-language Unit Test Generation with LLMs [6.259245181881262]
  We describe a generic pipeline that incorporates static analysis to guide LLMs in generating compilable and high-coverage test cases.<n>We conduct an empirical study to assess the quality of the generated tests in terms of code coverage and test naturalness.
  arXiv  Detail & Related papers  (2024-09-04T21:46:18Z)
• Leveraging Large Language Models for Enhancing the Understandability of Generated Unit Tests [4.574205608859157]
  We introduce UTGen, which combines search-based software testing and large language models to enhance the understandability of automatically generated test cases. We observe that participants working on assignments with UTGen test cases fix up to 33% more bugs and use up to 20% less time when compared to baseline test cases.
  arXiv  Detail & Related papers  (2024-08-21T15:35:34Z)
• SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents [10.730852617039451]
  We investigate the capability of LLM-based Code Agents to formalize user issues into test cases.<n>We propose a novel benchmark based on popular GitHub repositories, containing real-world issues, ground-truth bug-fixes, and golden tests.<n>We find that LLMs generally perform surprisingly well at generating relevant test cases, with Code Agents designed for code repair exceeding the performance of systems designed for test generation.
  arXiv  Detail & Related papers  (2024-06-18T14:54:37Z)

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.