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

arXiv: https://arxiv.org/abs/2510.05441 · HTML: https://mlsanity.com/paper/2510.05441/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Agent AI: Surveying the Horizons of Multimodal Interaction](https://mlsanity.com/paper/2401.03568/) (2024)
- [SWE-Lancer: Can Frontier LLMs Earn 1 Million from Real-World Freelance Software Engineering?](https://mlsanity.com/paper/2502.12115/) (2025)
- [Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM](https://mlsanity.com/paper/2402.00097/) (2024)
- [CoverUp: Effective High Coverage Test Generation for Python](https://mlsanity.com/paper/2403.16218/) (2024)
- [Code Red: The Business Impact of Code Quality -- A Quantitative Study of 39 Proprietary Production Codebases](https://mlsanity.com/paper/2203.04374/) (2022)
- [Evaluating LLM-Based Regression Test Generation](https://mlsanity.com/paper/2501.11086/) (2025)
- [The Evolution of Empirical Methods in Software Engineering](https://mlsanity.com/paper/1912.11512/) (2019)
- [Model Checking C++ Programs](https://mlsanity.com/paper/2107.01093/) (2021)
- [A Taxonomy of Information Attributes for Test Case Prioritisation: Applicability, Machine Learning](https://mlsanity.com/paper/2201.06044/) (2022)
- [Back to the Future! Studying Data Cleanness in Defects4J and its Impact on Fault Localization](https://mlsanity.com/paper/2310.19139/) (2023)
- [TracerX: Dynamic Symbolic Execution with Interpolation](https://mlsanity.com/paper/2012.00556/) (2020)
- [OrdinalFix: Fixing Compilation Errors via Shortest-Path CFL Reachability](https://mlsanity.com/paper/2309.06771/) (2023)

## Built on by (most cited first, 1 of 1)

- [Partial Contracts Suffice: Sound, LLM-Inferred Regression Verification](https://mlsanity.com/paper/2607.10291/) (2026)

## Abstract (arXiv)

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.