Page 32 - 《软件学报》2026年第7期

赵英全 等: 基于大语言模型的 Java 新特性测试程序生成 2717

generation. In: Proc. of the 2021 Conf. on Empirical Methods in Natural Language Processing. Punta Cana: ACL, 2021. 8696–8708.
[doi: 10.18653/v1/2021.emnlp-main.685]
[21] Xia CS, Paltenghi M, Tian JL, Pradel M, Zhang LM. Fuzz4All: Universal fuzzing with large language models. In: Proc. of the 46th
IEEE/ACM Int’l Conf. on Software Engineering. Lisbon: ACM, 2024. 126. [doi: 10.1145/3597503.3639121]
[22] Zhang BK, Zheng K. LumiX. 2025. https://github.com/zhang-bokai/LumiX
[23] Zhao YQ, Wang Z, Chen JJ, Liu MD, Wu MY, Zhang YQ, Zhang LM. History-driven test program synthesis for JVM testing. In: Proc.
of the 44th Int’l Conf. on Software Engineering. Pittsburgh: ACM, 2022. 1133–1144. [doi: 10.1145/3510003.3510059]
[24] Gao TC, Chen JJ, Zhao YQ, Zhang YQ, Zhang LM. Vectorizing program ingredients for better JVM testing. In: Proc. of the 32nd ACM
SIGSOFT Int’l Symp. on Software Testing and Analysis. Seattle: ACM, 2023. 526–537. [doi: 10.1145/3597926.3598075]
[25] Zhao YQ, Chen JJ, Fu RF, Ye HJ, Wang Z. Testing the compiler for a new-born programming language: An industrial case study
(experience paper). In: Proc. of the 32nd ACM SIGSOFT Int’l Symp. on Software Testing and Analysis. Seattle: ACM, 2023. 551–563.
[doi: 10.1145/3597926.3598077]
[26] Zang ZQ, Yu FY, Thimmaiah A, Shi A, Gligoric M. Java JIT testing with template extraction. Proc. of the ACM on Software
Engineering, 2024, 1(FSE): 1129–1151. [doi: 10.1145/3643777]
[27] Lidbury C, Lascu A, Chong N, Donaldson AF. Many-core compiler fuzzing. In: Proc. of the 36th ACM SIGPLAN Conf. on
Programming Language Design and Implementation. Portland: ACM, 2015. 65–76. [doi: 10.1145/2737924.2737986]
®
[28] Lindholm T, Yellin F, Bracha G, Buckley A, Smith D. The Java virtual machine specification. 2015. https://docs.oracle.com/javase/specs/
jvms/se24/html/index.html
[29] Zhao YQ, Wang Z, Chen JJ, Fu RF, Lu YZ, Gao TC, Ye HJ. Program ingredients abstraction and instantiation for synthesis-based JVM
testing. In: Proc. of the 2024 on ACM SIGSAC Conf. on Computer and Communications Security. Salt Lake City: ACM, 2024.
3943–3957. [doi: 10.1145/3658644.3690366]
[30] Ren XX, Ye XY, Lin Y, Xing ZC, Li SQ, Lyu MR. API-knowledge aware search-based software testing: Where, what, and how. In: Proc.
of the 31st ACM Joint European Software Engineering Conf. and Symp. on the Foundations of Software Engineering. San Francisco:
ACM, 2023. 1320–1332. [doi: 10.1145/3611643.3616269]
[31] Lin Y, Ong YS, Sun J, Fraser G, Dong JS. Graph-based seed object synthesis for search-based unit testing. In: Proc. of the 29th ACM
Joint Meeting on European Software Engineering Conf. and Symp. on the Foundations of Software Engineering. Athens: ACM, 2021.
1068–1080. [doi: 10.1145/3468264.3468619]
[32] Chen YT, Su T, Su ZD. Deep differential testing of JVM implementations. In: Proc. of the 41st Int’l Conf. on Software Engineering.
Montreal: IEEE, 2019. 1257–1268. [doi: 10.1109/ICSE.2019.00127]
[33] Chaliasos S, Sotiropoulos T, Spinellis D, Gervais A, Livshits B, Mitropoulos D. Finding typing compiler bugs. In: Proc. of the 43rd ACM
SIGPLAN Int’l Conf. on Programming Language Design and Implementation. San Diego: ACM, 2022. 183–198. [doi: 10.1145/3519939.
3523427]
[34] Jia HX, Wen M, Xie ZF, Guo XC, Wu RX, Sun ML, Chen K, Jin H. Detecting JVM JIT compiler bugs via exploring two-dimensional
input spaces. In: Proc. of the 45th IEEE/ACM Int’l Conf. on Software Engineering. Melbourne: IEEE, 2023. 43–55. [doi: 10.1109/
ICSE48619.2023.00016]
[35] Liu K, Koyuncu A, Kim D, Bissyandé TF. TBar: Revisiting template-based automated program repair. In: Proc. of the 28th ACM
SIGSOFT Int’l Symp. on Software Testing and Analysis. Beijing: ACM, 2019. 31–42. [doi: 10.1145/3293882.3330577]
[36] Zhao YQ. Silent acceptance of non-final variable in unreachable lambda expression #3792. 2025. https://github.com/eclipse-jdt/eclipse.
jdt.core/issues/3792
[37] Lu KM, Yu BW, Zhou C, Zhou JR. Large language models are superpositions of all characters: Attaining arbitrary role-play via self-
alignment. In: Proc. of the 62nd Annual Meeting of the Association for Computational Linguistics. Bangkok: ACL, 2024. 7828–7840.
[doi: 10.18653/v1/2024.acl-long.423]
[38] Wang ZJ, Zhou ZJ, Song D, Huang YH, Chen SM, Ma L, Zhang TY. Towards understanding the characteristics of code generation errors
made by large language models. In: Proc. of the 47th IEEE/ACM Int’l Conf. on Software Engineering. Ottawa: IEEE, 2025. 2587–2599.
[doi: 10.1109/ICSE55347.2025.00180]
[39] JaCoCo. JaCoCo Java code coverage library. 2025. https://www.eclemma.org/jacoco/
[40] GCov. 11 gcov—A test coverage program. 2025. https://gcc.gnu.org/onlinedocs/gcc/Gcov.html
[41] LCov. 2025. https://github.com/linux-test-project/lcov
[42] JavaParser. Tools for your Java code. 2025. https://javaparser.org/
[43] Qwen Team. Qwen2.5 technical report. arXiv:2412.15115, 2024.