UnitTenX: Generating Tests for Legacy Packages with AI Agents Powered by Formal Verification

Yiannis Charalambous, Claudionor N. Coelho, Luis Lamb, Lucas C. Cordeiro
10/6/2025
cs.SEcs.AI

No confident code implementation found for this paper.

Abstract

This paper introduces UnitTenX, a state-of-the-art open-source AI multi-agent system designed to generate unit tests for legacy code, enhancing test coverage and critical value testing. UnitTenX leverages a combination of AI agents, formal methods, and Large Language Models (LLMs) to automate test generation, addressing the challenges posed by complex and legacy codebases. Despite the limitations of LLMs in bug detection, UnitTenX offers a robust framework for improving software reliability and maintainability. Our results demonstrate the effectiveness of this approach in generating high-quality tests and identifying potential issues. Additionally, our approach enhances the readability and documentation of legacy code.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

The Potential of LLMs in Automating Software Testing: From Generation to Reporting

87% match2024

You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects

84% match1 repo732024

SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents

84% match1 repo852024

HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale

84% match1 repo2452024

Large Language Models as Test Case Generators: Performance Evaluation and Enhancement

83% match2024

Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol

83% match2025

Cite this paper

@article{charalambous2025unittenx,
  title  = {UnitTenX: Generating Tests for Legacy Packages with AI Agents Powered by Formal Verification},
  author = {Yiannis Charalambous and Claudionor N. Coelho and Luis Lamb and Lucas C. Cordeiro},
  year   = {2025},
  eprint = {2510.05441},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.05441v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.05441.svg)](https://codeofpaper.com/paper/2510.05441)

Discussion