Page 33 - 《软件学报》2026年第7期

2718 软件学报 2026 年第 37 卷第 7 期

[44] Alibaba Cloud Bailian. Tongyi Qianwen-max. 2025 (in Chinese). https://bailian.console.aliyun.com/model-market?tab=model#/model-
market/detail/qwen-max
[45] DeepSeek-AI. DeepSeek-V3 technical report. arXiv:2412.19437, 2025.
[46] Kang S, Yoon J, Askarbekkyzy N, Yoo S. Evaluating diverse large language models for automatic and general bug reproduction. IEEE
Trans. on Software Engineering, 2024, 50(10): 2677–2694. [doi: 10.1109/TSE.2024.3450837]
[47] Li J, Li G, Li YM, Jin Z. Structured chain-of-thought prompting for code generation. ACM Trans. on Software Engineering and
Methodology, 2015, 34(2): 37. [doi: 10.1145/3690635]
[48] Yang G, Zhou Y, Chen X, Zhang XY, Zhuo TY, Chen TL. Chain-of-thought in neural code generation: From and for lightweight
language models. IEEE Trans. on Software Engineering, 2024, 50(9): 2437–2457. [doi: 10.1109/TSE.2024.3440503]
[49] Zhang JW, Hu X, Xia X, Cheung SC, Li SP. Automated unit test generation via chain of thought prompt and reinforcement learning from
coverage feedback. ACM Trans. on Software Engineering and Methodology, 2025, 35(4): 1–30. [doi: 10.1145/3745765]
[50] Deng YL, Xia CS, Yang CY, Zhang SD, Yang SJ, Zhang LM. Large language models are edge-case generators: Crafting unusual
programs for fuzzing deep learning libraries. In: Proc. of the 46th IEEE/ACM Int’l Conf. on Software Engineering. Lisbon: ACM, 2024.
70. [doi: 10.1145/3597503.3623343]
[51] Wang Z, Zhao YQ, Liu S, Sun J, Chen X, Lin HR. MAP-coverage: A novel coverage criterion for testing thread-safe classes. In: Proc. of
the 34th IEEE/ACM Int’l Conf. on Automated Software Engineering. San Diego: IEEE, 2019. 722–734. [doi: 10.1109/ASE.2019.00073]
[52] Fuchs D. JEP 264: Platform logging API and service. 2014. https://openjdk.org/jeps/264

附中文参考文献
[44] 阿里云百炼. 通义千问-Max. 2025. https://bailian.console.aliyun.com/model-market?tab=model#/model-market/detail/qwen-max

作者简介
赵英全, 博士, 副研究员, CCF 专业会员, 主要研究领域为软件测试, 软件分析.
张博凯, 硕士生, 主要研究领域为软件测试.
王赞, 博士, 教授, CCF 专业会员, 主要研究领域为软件测试, 机器学习.
郭以勒, 硕士生, 主要研究领域为编译器测试.
陈佳丽, 副教授, 主要研究领域为智能软件工程.
陈翔, 博士, 副教授, CCF 高级会员, 主要研究领域为智能软件工程, 软件仓库挖掘, 经验软件工程.
陈俊洁, 博士, 教授, CCF 高级会员, 主要研究领域为软件分析与测试.