# ConCovUp: Effective Agent-Based Test Driver Generation for Concurrency Testing

arXiv: https://arxiv.org/abs/2605.09573 · HTML: https://mlsanity.com/paper/2605.09573/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 42 references that are in the map.
- First posted on arXiv 10 May 2026.

## Placed in

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

## Builds on (most cited first, 9 of 9)

- [ChatUniTest: A Framework for LLM-Based Test Generation](https://mlsanity.com/paper/2305.04764/) (2023)
- [CoverUp: Effective High Coverage Test Generation for Python](https://mlsanity.com/paper/2403.16218/) (2024)
- [HITS: High-coverage LLM-based Unit Test Generation via Method Slicing](https://mlsanity.com/paper/2408.11324/) (2024)
- [ASTER: Natural and Multi-language Unit Test Generation with LLMs](https://mlsanity.com/paper/2409.03093/) (2024)
- [Validating Network Protocol Parsers with Traceable RFC Document Interpretation](https://mlsanity.com/paper/2504.18050/) (2025)
- [Beware of the Unexpected: Bimodal Taint Analysis](https://mlsanity.com/paper/2301.10545/) (2023)
- [Fray: An Efficient General-Purpose Concurrency Testing Platform for the JVM (Extended Version)](https://mlsanity.com/paper/2501.12618/) (2025)
- [Efficient Timestamping for Sampling-based Race Detection](https://mlsanity.com/paper/2504.06688/) (2025)
- [Dynamic Race Detection With O(1) Samples](https://mlsanity.com/paper/2506.20127/) (2025)

## Abstract (arXiv)

Concurrency testing is essential to improve the reliability and security of multi-threaded programs. Dynamic analysis tools, such as TSan, depend on high-quality test drivers that reach critical shared-memory interactions at runtime. However, current testing practices predominantly focus on sequential logic, leaving a gap in automated concurrent test generation. Recently, large language models (LLMs) have shown promise in generating sequential tests, but they struggle to produce effective concurrent tests without a deep understanding of concurrency semantics. This paper presents ConCovUp, a multi-agent framework that combines LLMs with program analysis. ConCovUp grounds test generation in static analysis to extract shared memory accesses and their calling contexts. To trigger hard-to-reach accesses, it introduces an LLM-driven backward tracing approach, leveraging the model's semantic reasoning to deduce concrete inputs that satisfy complex path constraints, and iteratively refines the generated tests via dynamic execution feedback. Our evaluation on nine real-world C/C++ libraries shows that ConCovUp improves average Shared Memory Access Pair Coverage (SMAP Coverage) from 36.6% to 68.1% over the general Claude Code agent baseline.