ATTest: Agent-Driven Tensor Testing for Deep Learning Library Modules
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918339572400128 |
|---|---|
| author | Zhan, Zhengyu Shang, Ye Liu, Jiawei Fang, Chunrong Zhang, Quanjun Chen, Zhenyu |
| author_facet | Zhan, Zhengyu Shang, Ye Liu, Jiawei Fang, Chunrong Zhang, Quanjun Chen, Zhenyu |
| contents | The unit testing of Deep Learning (DL) libraries is challenging due to complex numerical semantics and implicit tensor constraints. Traditional Search-Based Software Testing (SBST) often suffers from semantic blindness, failing to satisfy the constraints of high-dimensional tensors, whereas Large Language Models (LLMs) struggle with cross-file context and unstable code modifications. This paper proposes ATTest, an agent-driven tensor testing framework for module-level unit test generation. ATTest orchestrates a seven-stage pipeline, which encompasses constraint extraction and an iterative "generation-validation-repair" loop, to maintain testing stability and mitigate context-window saturation. An evaluation on PyTorch and TensorFlow demonstrates that ATTest significantly outperforms state-of-the-art baselines such as PynguinML, achieving an average branch coverage of 55.60% and 54.77%, respectively. The results illustrate how agent-driven workflows bridge the semantic gap in numerical libraries while ensuring auditable test synthesis. Source code: https://github.com/iSEngLab/ATTest.git |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13987 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ATTest: Agent-Driven Tensor Testing for Deep Learning Library Modules Zhan, Zhengyu Shang, Ye Liu, Jiawei Fang, Chunrong Zhang, Quanjun Chen, Zhenyu Software Engineering The unit testing of Deep Learning (DL) libraries is challenging due to complex numerical semantics and implicit tensor constraints. Traditional Search-Based Software Testing (SBST) often suffers from semantic blindness, failing to satisfy the constraints of high-dimensional tensors, whereas Large Language Models (LLMs) struggle with cross-file context and unstable code modifications. This paper proposes ATTest, an agent-driven tensor testing framework for module-level unit test generation. ATTest orchestrates a seven-stage pipeline, which encompasses constraint extraction and an iterative "generation-validation-repair" loop, to maintain testing stability and mitigate context-window saturation. An evaluation on PyTorch and TensorFlow demonstrates that ATTest significantly outperforms state-of-the-art baselines such as PynguinML, achieving an average branch coverage of 55.60% and 54.77%, respectively. The results illustrate how agent-driven workflows bridge the semantic gap in numerical libraries while ensuring auditable test synthesis. Source code: https://github.com/iSEngLab/ATTest.git |
| title | ATTest: Agent-Driven Tensor Testing for Deep Learning Library Modules |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2602.13987 |