智能体
arxiv.org ·
ResTest：用大语言模型定向覆盖 Web GUI 测试中残余未覆盖代码
该论文提出 ResTest，一种对现有自动化 Web GUI 测试（AWGT）的补充方法：先运行现有 AWGT 广泛探索应用并构建带摘要信息的状态转移图，当覆盖率停滞时，用 LLM 基于状态转移图和覆盖率报告推断未覆盖功能，再由专门的 LLM 驱动 GUI agent 定向执行。在 10 个开源 Web 应用上，ResTest 将三类 AWGT 方法的平均代码覆盖率提升 17.52%–24.36%，消融实验验证了各组件贡献。
AI推荐理由 arXiv 论文（cs.SE），有明确作者、摘要与实验数据：在 10 个开源 Web 应用上，ResTest 使三类 AWGT 方法的平均代码覆盖率提升 17.52%–24.36%，并做了消融实验。新信息在于用覆盖率报告引导 LLM 推断未覆盖功能，再由 LLM 驱动的 GUI agent 定向执行，作为现有 AWGT 的补充而非替代。局限是仅在 10 个开源应用上评估，未给出与纯 LLM 方法的直接对比细节，且为 v2 修订版，实际工程落地效果仍需验证。
78
正文
Computer Science > Software Engineering
arXiv:2506.00520 (cs)
[Submitted on 31 May 2025 (v1), last revised 23 Sep 2026 (this version, v2)]
Title:ResTest: Targeted Coverage of Residual Not-Covered Code Using Large Language Models for Web GUI Testing
Authors:Chenxu Liu, Zhiyu Gu, Guoquan Wu, Ying Zhang, Wei Yang, Jun Wei, Tao Xie
View a PDF of the paper titled ResTest: Targeted Coverage of Residual Not-Covered Code Using Large Language Models for Web GUI Testing, by Chenxu Liu and 6 other authors
View PDF
HTML (experimental)
Abstract:Automated web GUI testing (AWGT) approaches explore web applications through GUI actions to achieve code coverage. However, existing approaches, whether random-based, model-based, or reinforcement-learning-based, often struggle to generate continuous and semantically meaningful action sequences for testing complex functionalities, limiting their achievable code coverage. Recent LLM-based approaches partially alleviate this problem but still fall short due to limited capability in inferring testable functionalities and low success rates in executing tasks on complex web applications.
In this paper, we propose ResTest, a complementary approach that uses coverage-report-guided LLMs to target residual not-covered code left by existing AWGT approaches. ResTest first runs an existing AWGT approach to broadly explore the application while constructing a state transition graph with summarized information. Once coverage plateaus, ResTest employs an LLM to infer not-covered functionalities based on the state transition graph and coverage report, and then utilizes a specialized LLM-driven GUI agent to execute these functionalities in a targeted manner.
Our evaluation on ten open-source web applications shows that ResTest improves three categories of AWGT approaches by 17.52\% to 24.36\% in average code coverage. Ablation studies further confirm the sustained coverage improvement capability and the contribution of each component.
Subjects:
Software Engineering (cs.SE)
Cite as:
arXiv:2506.00520 [cs.SE]
(or
arXiv:2506.00520v2 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2506.00520
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Chenxu Liu [view email]
[v1]
Sat, 31 May 2025 11:43:37 UTC (605 KB)
[v2]
Wed, 23 Sep 2026 11:25:31 UTC (369 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled ResTest: Targeted Coverage of Residual Not-Covered Code Using Large Language Models for Web GUI Testing, by Chenxu Liu and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.SE
new
|
recent
| 2025-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)