大模型
arxiv.org ·
NEUROTESTGEN：神经符号引导的大语言模型测试生成
该论文提出 NEUROTESTGEN，一种将符号执行与 LLM 测试合成结合的混合方法，用于按需代码覆盖的测试生成。给定方法内的目标语句，系统先用 Z3 SMT 求解器提取路径约束并构建符号引导规范，再据此引导 LLM 合成结构有效且语义合理的测试用例；对 SMT 难以处理的复杂对象约束，改由 LLM 推断。方法还包含迭代反馈循环，验证生成测试并给出纠正指导，直至覆盖目标行或分支。作者称在常用基准上，该方法在 Llama 3.3 70B、GPT-4o Mini、Claude 3.5 Haiku、Claude Sonnet 4.6 等多个 LLM 上显著优于现有方法。
AI推荐理由 arXiv 软件工程论文，提出 NEUROTESTGEN，将符号执行（Z3 SMT 求解器）与 LLM 测试合成结合，针对按需代码覆盖生成测试用例：先用符号分析提取路径约束形成引导规范，再让 LLM 合成可执行测试，对 SMT 难以处理的复杂对象约束由 LLM 推断，并加入迭代反馈循环直至覆盖目标行/分支。摘要称在常用基准上优于现有方法，覆盖 Llama 3.3 70B、GPT-4o Mini、Claude 3.5 Haiku、Claude Sonnet 4.6 等多个模型。新信息明确、方法可复现，对 AI 辅助软件测试与 Agent 工具有参考价值；局限是仅有摘要级证据，未给出具体覆盖率数字与基准名称，效果需看全文验证。
72
正文
Computer Science > Software Engineering
arXiv:2609.30178 (cs)
[Submitted on 24 Sep 2026]
Title:NEUROTESTGEN: Neuro-Symbolic Guided Test Generation with Large Language Models
Authors:Ruixin Zhang, Jiho Shin, Hung Viet Pham, Song Wang
View a PDF of the paper titled NEUROTESTGEN: Neuro-Symbolic Guided Test Generation with Large Language Models, by Ruixin Zhang and 3 other authors
View PDF
HTML (experimental)
Abstract:Ensuring high structural coverage remains a fundamental challenge in automated test generation, particularly for complex software systems where reaching specific lines or branches requires satisfying intricate control- and data-flow constraints. Large Language Models (LLMs) have recently demonstrated strong capabilities in producing human-like test cases; however, they often struggle to generate inputs that satisfy precise path conditions. Conversely, symbolic execution can systematically derive such constraints, but it often fails to construct realistic, executable test cases and is constrained by scalability limitations.
In this paper, we introduce NEUROTESTGEN, a hybrid approach that integrates symbolic execution with LLM-driven test synthesis to generate test cases targeting on-demand code coverage. Given a set of target statements within a method, NEUROTESTGEN first employs a symbolic analysis engine (i.e., the Z3 SMT solver) to extract path-specific constraints and construct a symbolic guidance specification for the desired coverage goal. This specification is then used to guide an LLM in synthesizing concrete test cases that are both structurally valid and semantically meaningful. For paths involving complex object-related constraints that are difficult for SMT solvers to handle, NEUROTESTGEN leverages LLMs to infer plausible constraints. Furthermore, NEUROTESTGEN incorporates an iterative feedback loop that validates LLM-generated tests and provides corrective guidance until the target line or branch is covered or a limit is reached. Our empirical evaluation on a widely used benchmark demonstrates that NEUROTESTGEN significantly outperforms the state-of-the-art approach across multiple LLMs, including Llama 3.3 70B1, GPT-4o Mini, Claude 3.5 Haiku3, and Claude Sonnet 4.6.
Subjects:
Software Engineering (cs.SE)
Cite as:
arXiv:2609.30178 [cs.SE]
(or
arXiv:2609.30178v1 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2609.30178
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Song Wang [view email]
[v1]
Thu, 24 Sep 2026 17:27:04 UTC (2,356 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled NEUROTESTGEN: Neuro-Symbolic Guided Test Generation with Large Language Models, by Ruixin Zhang and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.SE
new
|
recent
| 2026-09
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?)